Model Analysis
Nikhil Gupta
2019-02-11 18:28:54
sessionInfo()## R version 3.5.1 (2018-07-02)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 17134)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=English_United States.1252
## [2] LC_CTYPE=English_United States.1252
## [3] LC_MONETARY=English_United States.1252
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## loaded via a namespace (and not attached):
## [1] compiler_3.5.1 magrittr_1.5 tools_3.5.1 htmltools_0.3.6
## [5] yaml_2.2.0 Rcpp_1.0.0 stringi_1.2.4 rmarkdown_1.11
## [9] knitr_1.20 stringr_1.3.1 digest_0.6.18 evaluate_0.12User Inputs
output.var = params$output.var
transform.abs = params$transform.abs
log.pred = params$log.pred
eda = params$eda
algo.forward = params$algo.forward
algo.backward = params$algo.backward
algo.stepwise = params$algo.stepwise
algo.LASSO = params$algo.LASSO
algo.LARS = params$algo.LARS
algo.forward.caret = params$algo.forward.caret
algo.backward.caret = params$algo.backward.caret
algo.stepwise.caret = params$algo.stepwise.caret
algo.LASSO.caret = params$algo.LASSO.caret
algo.LARS.caret = params$algo.LARS.caret
message("Parameters used for training/prediction: ")## Parameters used for training/prediction:str(params)## List of 14
## $ output.var : chr "y3"
## $ transform.abs : logi FALSE
## $ log.pred : logi FALSE
## $ eda : logi TRUE
## $ algo.forward : logi FALSE
## $ algo.backward : logi FALSE
## $ algo.stepwise : logi FALSE
## $ algo.LASSO : logi FALSE
## $ algo.LARS : logi FALSE
## $ algo.forward.caret : logi FALSE
## $ algo.backward.caret: logi FALSE
## $ algo.stepwise.caret: logi FALSE
## $ algo.LASSO.caret : logi FALSE
## $ algo.LARS.caret : logi FALSE# Setup Labels
# alt.scale.label.name = Alternate Scale variable name
# - if predicting on log, then alt.scale is normal scale
# - if predicting on normal scale, then alt.scale is log scale
if (log.pred == TRUE){
label.names = paste('log.',output.var,sep="")
alt.scale.label.name = output.var
}
if (log.pred == FALSE){
label.names = output.var
alt.scale.label.name = paste('log.',output.var,sep="")
}Prepare Data
Read and Clean Features
features = read.csv("../../Data/features.csv")
features.highprec = read.csv("../../Data/features_highprec.csv")all.equal(features, features.highprec)## [1] "Component \"x11\": Mean relative difference: 0.001401482"
## [2] "Component \"stat9\": Mean relative difference: 0.0002946299"
## [3] "Component \"stat12\": Mean relative difference: 0.0005151515"
## [4] "Component \"stat13\": Mean relative difference: 0.001354369"
## [5] "Component \"stat18\": Mean relative difference: 0.0005141104"
## [6] "Component \"stat22\": Mean relative difference: 0.001135977"
## [7] "Component \"stat25\": Mean relative difference: 0.0001884615"
## [8] "Component \"stat29\": Mean relative difference: 0.001083691"
## [9] "Component \"stat36\": Mean relative difference: 0.00021513"
## [10] "Component \"stat37\": Mean relative difference: 0.0004578125"
## [11] "Component \"stat43\": Mean relative difference: 0.0003473684"
## [12] "Component \"stat45\": Mean relative difference: 0.0002951699"
## [13] "Component \"stat46\": Mean relative difference: 0.0009745763"
## [14] "Component \"stat47\": Mean relative difference: 8.829902e-05"
## [15] "Component \"stat55\": Mean relative difference: 0.001438066"
## [16] "Component \"stat57\": Mean relative difference: 0.0001056911"
## [17] "Component \"stat58\": Mean relative difference: 0.0004882261"
## [18] "Component \"stat60\": Mean relative difference: 0.0002408377"
## [19] "Component \"stat62\": Mean relative difference: 0.0004885106"
## [20] "Component \"stat66\": Mean relative difference: 1.73913e-06"
## [21] "Component \"stat67\": Mean relative difference: 0.0006265823"
## [22] "Component \"stat73\": Mean relative difference: 0.003846154"
## [23] "Component \"stat75\": Mean relative difference: 0.002334906"
## [24] "Component \"stat83\": Mean relative difference: 0.0005628415"
## [25] "Component \"stat86\": Mean relative difference: 0.0006104418"
## [26] "Component \"stat94\": Mean relative difference: 0.001005115"
## [27] "Component \"stat97\": Mean relative difference: 0.0003551913"
## [28] "Component \"stat98\": Mean relative difference: 0.0006157635"
## [29] "Component \"stat106\": Mean relative difference: 0.0008267717"
## [30] "Component \"stat109\": Mean relative difference: 0.0005121359"
## [31] "Component \"stat110\": Mean relative difference: 0.0007615527"
## [32] "Component \"stat111\": Mean relative difference: 0.001336134"
## [33] "Component \"stat114\": Mean relative difference: 7.680492e-05"
## [34] "Component \"stat117\": Mean relative difference: 0.0002421784"
## [35] "Component \"stat122\": Mean relative difference: 0.0006521084"
## [36] "Component \"stat123\": Mean relative difference: 8.333333e-05"
## [37] "Component \"stat125\": Mean relative difference: 0.002385135"
## [38] "Component \"stat130\": Mean relative difference: 0.001874016"
## [39] "Component \"stat132\": Mean relative difference: 0.0003193182"
## [40] "Component \"stat135\": Mean relative difference: 0.0001622517"
## [41] "Component \"stat136\": Mean relative difference: 7.722008e-05"
## [42] "Component \"stat138\": Mean relative difference: 0.0009739953"
## [43] "Component \"stat143\": Mean relative difference: 0.0004845361"
## [44] "Component \"stat146\": Mean relative difference: 0.0005821596"
## [45] "Component \"stat148\": Mean relative difference: 0.0005366922"
## [46] "Component \"stat153\": Mean relative difference: 0.0001557522"
## [47] "Component \"stat154\": Mean relative difference: 0.001351916"
## [48] "Component \"stat157\": Mean relative difference: 0.0005427928"
## [49] "Component \"stat162\": Mean relative difference: 0.002622951"
## [50] "Component \"stat167\": Mean relative difference: 0.0005905172"
## [51] "Component \"stat168\": Mean relative difference: 0.0002791096"
## [52] "Component \"stat169\": Mean relative difference: 0.0004121827"
## [53] "Component \"stat170\": Mean relative difference: 0.0004705882"
## [54] "Component \"stat174\": Mean relative difference: 0.0003822894"
## [55] "Component \"stat179\": Mean relative difference: 0.0008286604"
## [56] "Component \"stat184\": Mean relative difference: 0.0007526718"
## [57] "Component \"stat187\": Mean relative difference: 0.0005122768"
## [58] "Component \"stat193\": Mean relative difference: 4.215116e-05"
## [59] "Component \"stat199\": Mean relative difference: 0.002155844"
## [60] "Component \"stat203\": Mean relative difference: 0.0003738318"
## [61] "Component \"stat213\": Mean relative difference: 0.000667676"
## [62] "Component \"stat215\": Mean relative difference: 0.0003997955"head(features)## JobName x1 x2 x3 x4 x5 x6
## 1 Job_00001 2.0734508 4.917267 19.96188 3.520878 7.861051 1.6067589
## 2 Job_00002 2.2682543 4.955773 19.11939 19.763031 6.931355 1.3622041
## 3 Job_00003 1.7424456 2.059819 13.37912 38.829132 6.274053 2.0529845
## 4 Job_00004 0.7873555 2.613983 17.23044 64.402557 5.377652 0.9067419
## 5 Job_00005 2.3342753 4.299076 14.64883 52.537304 6.793368 2.4605792
## 6 Job_00006 1.2365089 2.795370 11.13127 96.819939 6.583971 2.3510606
## x7 x8 x9 x10 x11 x12 x13
## 1 2.979479 8.537228 1.103368 4.6089458 1.05e-07 7.995825 13.215498
## 2 2.388119 6.561461 0.588572 1.0283282 1.03e-07 7.486966 22.557224
## 3 2.043592 10.275595 4.834385 4.3872848 1.06e-07 6.350142 15.049810
## 4 2.395118 13.487331 3.340190 4.5053501 9.47e-08 9.548698 17.170635
## 5 2.891535 9.362389 1.246039 1.7333300 1.01e-07 9.596095 5.794567
## 6 1.247838 7.033354 1.852231 0.4839371 1.07e-07 3.810983 23.863169
## x14 x15 x16 x17 x18 x19 x20
## 1 4.377983 0.2370623 6.075459 3.988347 4.767475 2.698775 1.035893
## 2 2.059315 0.5638121 6.903891 4.152054 6.849232 9.620731 1.915288
## 3 3.260057 2.0603445 8.424065 4.489893 3.493591 4.715386 1.558103
## 4 3.093478 1.8806034 11.189792 2.134271 5.588357 5.107871 1.489588
## 5 3.943076 1.5820830 7.096742 3.563378 7.765610 1.360272 1.240283
## 6 1.280562 1.1733382 7.062051 1.341864 7.748325 5.009365 1.725179
## x21 x22 x23 stat1 stat2 stat3 stat4
## 1 42.36548 1.356213 2.699796 2.3801832 0.1883335 -1.2284011 -0.5999233
## 2 26.63295 4.053961 2.375127 -1.4069480 1.8140973 1.6204884 2.6422672
## 3 20.09693 3.079888 4.488420 -0.7672566 -0.1230289 1.1415752 2.9805934
## 4 32.60415 1.355396 3.402398 0.4371202 -1.9355906 0.9028624 -1.6025400
## 5 44.58361 1.940301 2.249011 2.4492466 -0.6172000 -2.5520642 -2.1485929
## 6 28.75102 2.500499 5.563972 -1.7899084 1.8853619 2.4154840 -2.6022179
## stat5 stat6 stat7 stat8 stat9 stat10
## 1 0.148893163 -0.6622978 -2.4851868 0.3647782 2.5364335 2.92067981
## 2 1.920768980 1.7411555 -1.9599979 -2.0190558 -1.3732762 -0.31642506
## 3 2.422584300 -0.4166040 2.2205689 -2.6741531 0.4844292 2.73379230
## 4 -0.001795933 -0.6946563 -0.3693534 -0.9709467 1.7960306 0.74771154
## 5 -2.311132430 -1.0166832 2.7269876 1.5424492 -1.3156369 -0.09767897
## 6 -1.785491470 -1.8599915 1.4875095 2.0188572 -1.4892503 -1.41103566
## stat11 stat12 stat13 stat14 stat15 stat16
## 1 -2.3228905 -2.480567 -0.6335157 -0.3650149 -0.5322812 0.6029300
## 2 -0.8547903 1.119316 0.7227427 0.2121097 -0.1452281 -2.0361528
## 3 -2.1821580 2.865401 -2.9756081 2.9871745 1.9539525 -1.8857163
## 4 1.3982378 1.856765 -1.0379983 2.3341896 2.3057184 -2.8947697
## 5 0.9567220 2.567549 0.3184886 1.0307668 0.1644241 -0.6613821
## 6 0.5341771 -1.461822 0.4402476 -1.9282095 -0.3680157 1.8188807
## stat17 stat18 stat19 stat20 stat21 stat22
## 1 -1.04516208 2.3544915 2.4049001 0.2633883 -0.9788178 1.7868229
## 2 0.09513074 0.4727738 1.8899702 2.7892542 -1.3919091 -1.7198164
## 3 0.40285346 1.4655282 -1.4952788 2.9162340 -2.3893208 2.8161423
## 4 2.97446084 2.3896182 2.3083484 -1.1894441 -2.1982553 1.3666242
## 5 -0.98465055 0.6900643 1.5894209 -2.1204538 1.7961155 -0.9362189
## 6 -1.45726359 -2.1139548 -0.3964904 1.1764175 -2.9100556 -2.1359294
## stat23 stat24 stat25 stat26 stat27 stat28
## 1 -2.3718851 2.8580718 -0.4719713 -2.817086 -0.9518474 2.88892484
## 2 -2.3293245 1.5577759 -1.9569720 1.554194 -0.5081459 -1.58715141
## 3 -2.5402296 0.1422861 0.3572798 -1.051886 -2.1541717 0.03074004
## 4 -1.9679050 -1.4077642 2.5097435 1.683121 -0.2549745 -2.90384054
## 5 2.0523429 -2.2084844 -1.9280857 -2.116736 1.8180779 -1.42167580
## 6 0.2184991 -0.7599817 2.6880329 -2.903350 -1.0733233 -2.92416644
## stat29 stat30 stat31 stat32 stat33 stat34
## 1 0.7991088 -2.0059092 -0.2461502 0.6482101 -2.87462163 -0.3601543
## 2 1.9758110 -0.3874187 1.3566630 2.6493473 2.28463054 1.8591728
## 3 -0.4460218 1.0279679 1.3998452 -1.0183365 1.41109037 -2.4183984
## 4 1.0571996 2.5588036 -2.9830337 -1.1299983 0.05470414 -1.5566561
## 5 0.8854889 2.2774174 2.6499031 2.3053405 -2.39148426 -1.8272992
## 6 -0.8405267 0.1311945 0.4321289 -2.9622040 -2.55387473 2.6396458
## stat35 stat36 stat37 stat38 stat39 stat40
## 1 2.4286051 -0.5420244 -2.6782637 -2.8874269 -0.8945006 1.1749642
## 2 1.3709245 -1.3714181 1.3901204 1.2273489 -0.8934880 1.0540369
## 3 -0.9805572 2.0571353 0.8845031 2.0574493 1.1222047 1.8528618
## 4 1.0969149 -2.2820673 1.8852408 0.5391517 2.7334342 -0.4372566
## 5 -1.0971669 1.4867796 -2.3738465 -0.3743561 1.4266498 1.2551680
## 6 0.4584349 -2.2696617 -0.9935142 -0.5350499 -0.7874799 2.0009417
## stat41 stat42 stat43 stat44 stat45 stat46
## 1 -1.0474428 -1.3909023 2.54110503 -1.4320793 0.6298335 -2.09296608
## 2 2.5380247 1.6476108 0.44128850 -2.5049477 1.2726039 1.72492969
## 3 1.1477574 0.2288794 0.08891252 2.3044751 -0.7735722 -0.07302936
## 4 -1.3808300 -2.7900956 2.38297582 0.1686397 -2.1591296 1.60828602
## 5 0.2257536 1.9542116 2.66429019 0.8026123 -1.5521187 1.61751962
## 6 -1.3364114 -2.2898803 2.80735397 -0.8413086 1.0057797 -1.50653386
## stat47 stat48 stat49 stat50 stat51 stat52
## 1 -2.8318939 2.1445766 0.5668035 0.1544579 0.6291955 2.2197027
## 2 -0.5804687 -1.3689737 1.4908396 1.2465997 0.8896304 -2.6024318
## 3 0.7918019 1.5712964 1.1038082 -0.2545658 -2.1662638 0.2660159
## 4 -1.8894132 0.5680230 -0.7023218 -0.3972188 0.1578027 2.1770194
## 5 2.1088455 -2.7195437 2.1961412 -0.2615084 1.2109556 0.8260623
## 6 -1.4400891 -0.9421459 -1.7324599 -2.1720727 -2.8129435 0.6958785
## stat53 stat54 stat55 stat56 stat57 stat58
## 1 2.176805 0.5546907 -2.19704103 -0.2884173 1.3232913 -1.32824039
## 2 -2.107441 1.3864788 0.08781975 1.9998228 0.8014438 -0.26979154
## 3 1.234197 2.1337581 1.65231645 -0.4388691 -0.1811156 2.11277962
## 4 2.535406 -2.1387620 0.12856023 -1.9906180 0.9626449 1.65232646
## 5 -2.457080 2.1633499 0.60441124 2.5449364 -1.4978440 2.60542655
## 6 2.003033 -0.5379940 -2.19647264 -1.1954677 -0.5974466 -0.04703835
## stat59 stat60 stat61 stat62 stat63 stat64
## 1 1.24239659 -2.5798278 1.327928 1.68560362 0.6284891 -1.6798652
## 2 0.06379301 0.9465770 1.116928 0.03128772 -2.1944375 0.3382609
## 3 0.93223447 2.4597080 0.465251 -1.71033382 -0.5156728 1.8276784
## 4 -0.29840910 0.7273473 -2.313066 -1.47696018 2.5910559 -1.5127999
## 5 -1.17610002 -1.7948418 -2.669305 0.17813617 2.8956099 2.9411416
## 6 -1.01793981 0.2817057 2.228023 -0.86494124 -0.9747949 -0.1569053
## stat65 stat66 stat67 stat68 stat69 stat70
## 1 -2.9490898 -0.3325469 1.5745990 -2.2978280 1.5451891 -1.345990
## 2 -1.1174885 -1.5728682 -2.9229002 0.2658547 -1.9616533 2.506130
## 3 -0.2231264 -0.4503301 0.7932286 -1.2453773 -2.2309763 2.309761
## 4 -0.3522418 -2.0720532 0.9442933 2.9212906 0.5100371 -2.441108
## 5 -2.1648991 1.2002029 2.8266985 0.7461294 1.6772674 -1.280000
## 6 -2.2295458 1.1446493 0.2024925 -0.2983998 -2.8203752 1.224030
## stat71 stat72 stat73 stat74 stat75 stat76
## 1 1.0260956 2.1071210 2.6625669 -2.8924677 -0.02132523 -2.5058765
## 2 0.3525076 1.6922342 -1.2167022 -1.7271879 2.21176434 1.9329683
## 3 -2.1799035 -2.2645276 0.1415582 0.9887453 1.95592320 0.2951785
## 4 -2.4051409 2.0876484 -0.8632146 0.4011389 -1.16986716 -1.2391174
## 5 1.3538754 -0.8089395 -0.5122626 -2.1696892 1.07344925 2.6696169
## 6 -2.8073371 -1.4450488 0.5481212 -1.4381690 0.80917043 -0.1365944
## stat77 stat78 stat79 stat80 stat81 stat82
## 1 -2.5631845 -2.40331340 0.38416120 -1.2564875 -0.1550840 -1.1762617
## 2 -0.4462085 0.38400793 1.80483031 -0.8387642 0.7624431 0.9936900
## 3 1.6757870 -1.81900752 2.70904708 -0.3201959 2.5754235 1.6346260
## 4 -2.1012006 -2.24691081 1.78056848 1.0323739 1.0762523 2.1343851
## 5 -2.5736733 -1.99958372 -0.05388495 -2.5630073 -2.8783002 -0.5752426
## 6 1.6143972 0.03233746 2.90835762 1.4000487 2.9275615 -2.8503830
## stat83 stat84 stat85 stat86 stat87 stat88
## 1 1.2840565 -2.6794965 1.3956039 -1.5290235 2.221152 2.3794982
## 2 -0.2380048 1.9314318 -1.6747955 -0.3663656 1.582659 -0.5222489
## 3 -0.9150769 -1.5520337 2.4186287 2.7273662 1.306642 0.1320062
## 4 -2.5824408 -2.7775943 0.5085060 0.4689015 2.053348 0.7957955
## 5 -1.0017741 -0.2009138 0.3770109 2.4335201 -1.118058 1.3953410
## 6 2.4891765 2.9931953 -1.4171852 0.3905659 -1.856119 -2.1690490
## stat89 stat90 stat91 stat92 stat93 stat94
## 1 -0.9885110 -0.8873261 -2.7810929 -1.53325891 2.6002395 1.8890998
## 2 0.9982028 -1.2382015 -0.1574496 0.41086048 -0.5412626 -0.2421387
## 3 0.5956759 1.6871066 2.2452753 2.74279594 -1.5860478 2.9393122
## 4 2.0902634 2.1752586 -2.0677712 -2.37861037 1.1653302 0.1500632
## 5 2.9820614 0.8111660 -0.7842287 0.03766387 -1.1681970 2.1217251
## 6 -1.7428021 0.1579032 1.7456742 -0.36858466 -0.1304616 -1.4555819
## stat95 stat96 stat97 stat98 stat99 stat100
## 1 -2.6056035 -0.5814857 2.57652426 -2.3297751 2.6324007 1.445827
## 2 -2.0271583 -0.9126074 2.49582648 0.9745382 1.1339203 -2.549544
## 3 0.3823181 -0.6324139 2.46221566 1.1151560 0.4624891 0.107072
## 4 2.6414623 -0.6630505 2.10394859 1.2627635 0.4861740 1.697012
## 5 1.4642254 2.6485956 -0.07699547 0.6219473 -1.8815142 -2.685463
## 6 1.8937331 -0.4690555 1.04671776 -0.5879866 -0.9766789 2.405940
## stat101 stat102 stat103 stat104 stat105 stat106
## 1 -2.1158021 2.603936 1.7745128 -1.8903574 -1.8558655 1.0122044
## 2 -2.7998588 -2.267895 0.5336456 -0.2859477 -0.5196246 -0.9417582
## 3 0.7969509 -1.744906 -0.7960327 1.9767258 -0.2007264 -0.7872376
## 4 1.7071959 -1.540221 1.6770362 1.5395796 -0.4855365 -1.2894115
## 5 -1.4627420 -1.700983 2.4376490 0.2731541 1.5275587 1.3256483
## 6 2.6888530 1.090155 2.0769854 1.9615480 1.8689761 2.8975825
## stat107 stat108 stat109 stat110 stat111 stat112
## 1 1.954508 -0.3376471 2.503084 0.3099165 2.7209847 -2.3911204
## 2 -2.515160 0.3998704 -1.077093 2.4228268 -0.7759693 0.2513882
## 3 1.888827 1.5819857 -2.066659 -2.0008364 0.6997684 2.6157095
## 4 1.076395 -1.8524148 -2.689204 1.0985872 1.2389493 2.1018629
## 5 2.828866 -1.8590252 -2.424163 1.4391942 -0.6173239 -1.5218846
## 6 -1.419639 0.7888914 1.996463 0.9813507 0.9034198 1.3810679
## stat113 stat114 stat115 stat116 stat117 stat118
## 1 -1.616161 1.0878664 0.9860094 -0.06288462 -1.013501 -1.2212842
## 2 -1.554771 1.8683100 0.4880588 -0.63865489 -1.610217 -1.7713343
## 3 -2.679801 -2.9486952 1.7753417 0.90311784 -1.318836 -0.1429040
## 4 2.459229 -0.5584171 0.4419581 -0.09586351 0.595442 0.2883342
## 5 -2.102200 1.6300170 -2.3498287 1.36771894 -1.912202 -0.2563821
## 6 -1.835037 0.6577786 -2.9928374 2.13540316 -1.437299 -0.9570006
## stat119 stat120 stat121 stat122 stat123 stat124
## 1 2.9222729 1.9151262 1.6686068 2.0061224 1.5723072 0.78819227
## 2 2.1828208 0.8283178 -2.4458632 1.7133740 1.1393738 -0.07182054
## 3 0.9721319 1.2723130 2.8002086 2.7670381 -2.2252586 2.17499113
## 4 -1.9327896 -2.5369370 1.7835028 1.0262097 -1.8790983 -0.43639564
## 5 1.3230809 -2.8145256 -0.9547533 -2.0435417 -0.2758764 -1.85668027
## 6 0.1720700 -1.4568460 1.4115051 -0.9878145 2.3895061 -2.33730745
## stat125 stat126 stat127 stat128 stat129 stat130
## 1 1.588372 1.1620011 -0.2474264 1.650328 2.5147598 0.37283245
## 2 -1.173771 0.8162020 0.3510315 -1.263667 1.7245284 -0.72852904
## 3 -1.503497 -0.5656394 2.8040256 -2.139287 -1.7221642 2.17899609
## 4 1.040967 -2.9039600 0.3103742 1.462339 -1.2940350 -2.95015502
## 5 -2.866184 1.6885070 -2.2525666 -2.628631 1.8581577 2.80127025
## 6 -1.355111 1.5017927 0.4295921 -0.580415 0.9851009 -0.03773117
## stat131 stat132 stat133 stat134 stat135 stat136
## 1 -0.09028241 0.5194538 2.8478346 2.6664724 -2.0206311 1.398415090
## 2 -0.53045595 1.4134049 2.9180586 0.3299096 1.4784122 -1.278896090
## 3 1.35843194 0.2279946 0.3532595 0.6138676 -0.3443284 0.057763811
## 4 -1.92450273 1.2698178 -1.5299660 -2.6083462 1.1665530 -0.187791914
## 5 1.49036849 2.6337729 -2.3206244 0.4978287 -1.7397571 0.001200184
## 6 -0.64642709 -1.9256228 1.7032650 -0.9152725 -0.3188055 2.155395980
## stat137 stat138 stat139 stat140 stat141 stat142
## 1 -1.2794871 0.4064890 -0.4539998 2.6660173 -1.8375313 0.4711883
## 2 -2.7709017 -1.6303773 -1.9025910 0.2572918 0.6612002 1.4764348
## 3 -1.1930757 -0.1051243 -0.5108380 -1.0879666 2.4969513 -0.9477230
## 4 -1.2318919 2.2348571 0.1788580 -1.5851788 -1.2384283 -2.1859181
## 5 1.8685058 2.7229517 -2.9077182 2.6606939 -1.5963592 -2.2213492
## 6 -0.4807318 -1.2117369 -0.9358531 -2.5100758 -2.3803916 -0.7096854
## stat143 stat144 stat145 stat146 stat147 stat148
## 1 1.9466263 2.2689433 -0.3597288 -0.6551386 1.65438592 0.6404466
## 2 1.3156421 2.4459090 -0.3790028 1.4858465 -0.07784461 1.0096149
## 3 0.1959563 2.3062942 1.8459278 2.6848175 -2.70935774 -1.2093409
## 4 1.7633296 -2.8171508 2.0902622 -2.6625464 -1.12600601 -2.1926479
## 5 0.3885758 1.8160636 2.8257299 -1.4526173 1.60679603 2.3807991
## 6 0.7623450 0.2692145 -2.4307463 -2.1244523 -2.67803812 -1.5273387
## stat149 stat150 stat151 stat152 stat153 stat154
## 1 0.1583575 0.4755351 0.3213410 2.0241520 1.5720103 -0.1825875
## 2 -0.4311406 2.9577663 0.6937252 0.1397280 0.3775735 -1.1012636
## 3 -0.8352824 2.5716205 1.7528236 0.4326277 -2.2334397 -2.6265771
## 4 -2.8069143 1.8813509 2.3358023 0.1015632 1.2117474 -1.3714278
## 5 -1.6166265 1.1112266 -1.1998471 2.9316769 -2.1676455 -0.3411089
## 6 -0.2265472 2.7264354 -1.6746094 -2.3376281 -1.7022788 -1.2352397
## stat155 stat156 stat157 stat158 stat159 stat160
## 1 -1.139657 0.07061254 0.5893906 -1.9920996 -2.83714366 2.249398
## 2 -2.041093 0.74047768 2.5415072 -1.2697256 -1.64364433 -2.448922
## 3 -1.219507 -0.55198693 0.4046920 1.2098547 -0.90412390 -1.934093
## 4 2.992191 2.33222485 2.0622969 -0.6714653 2.76836085 -1.431120
## 5 -2.362356 -1.23906672 0.4746319 -0.7849202 0.69399995 2.052411
## 6 -1.604499 1.31051409 -0.5164744 0.6288667 0.07899523 -2.287402
## stat161 stat162 stat163 stat164 stat165 stat166
## 1 1.7182635 -1.2323593 2.7350423 1.0707235 1.1621544 0.9493989
## 2 -0.6247674 2.6740098 2.8211024 1.5561292 -1.1027147 1.0519739
## 3 -0.6230453 -0.7993517 -2.8318374 -1.1148673 1.4261659 0.5294309
## 4 1.7644744 0.1696584 1.2653207 0.6621516 0.9470508 0.1985014
## 5 -1.2070210 0.7243784 0.9736322 2.7426259 -2.6862383 1.6840212
## 6 2.3705316 -2.1667893 -0.2516685 -0.8425958 -1.9099342 -2.8607297
## stat167 stat168 stat169 stat170 stat171 stat172
## 1 0.1146510 2.3872008 1.1180918 -0.95370555 -2.25076509 0.2348182
## 2 1.0760417 -2.0449336 0.9715676 -0.40173489 -0.11953555 -2.3107369
## 3 1.1735898 1.3860190 -2.2894719 0.06350347 0.29191551 -1.6079744
## 4 2.5511832 0.5446648 1.2694012 -0.84571201 0.79789722 0.2623538
## 5 2.2900002 2.6289782 -0.2783571 1.39032829 -0.55532032 1.0499046
## 6 -0.7513983 2.9617066 -2.2119520 -1.71958113 -0.01452018 -0.2751517
## stat173 stat174 stat175 stat176 stat177 stat178
## 1 1.79366076 -1.920206 -0.38841942 0.8530301 1.64532077 -1.1354179
## 2 -0.07484659 1.337846 2.20911694 0.9616837 -2.80810070 -2.1136749
## 3 -1.05521810 -1.483741 0.06148359 2.3066039 -0.34688616 1.1840581
## 4 0.31460321 1.195741 2.97633862 1.1685091 -0.06346265 1.4205489
## 5 -1.39428365 2.458523 0.64836472 -1.0396386 -0.57828104 -0.5006818
## 6 2.31844401 1.239864 -2.06490874 0.7696204 -1.77586019 2.0855925
## stat179 stat180 stat181 stat182 stat183 stat184
## 1 2.0018647 0.1476815 -1.27279520 1.9181504 -0.5297624 -2.9718938
## 2 -2.1351449 2.9012582 -1.09914911 -2.5488517 -2.8377736 1.4073374
## 3 -1.7819908 2.9902627 0.81908613 0.2503852 0.3712984 -2.1714024
## 4 -0.1026974 -2.4763253 -2.52645421 1.3096315 2.1458161 -1.5228094
## 5 -2.2298794 2.4465680 -0.70346898 -1.6997617 2.9178164 -0.3615532
## 6 -1.1168108 1.5552123 -0.01361342 1.7338791 -1.1104763 0.1882416
## stat185 stat186 stat187 stat188 stat189 stat190
## 1 -0.1043832 -1.5047463 2.700351 -2.4780862 -1.9078265 0.9978108
## 2 -2.0310574 -0.5380074 -1.963275 -1.2221278 -2.4290681 -1.9515115
## 3 2.6727278 1.2688179 -1.399018 -2.9612138 2.6456394 2.0073323
## 4 -2.7796295 2.0682354 2.243727 0.4296881 0.1931333 2.2710960
## 5 -0.6231265 2.5833981 2.229041 0.8139584 1.4544131 1.8886451
## 6 2.7204690 -2.4469144 -1.421998 1.7477882 -0.1481806 0.6011560
## stat191 stat192 stat193 stat194 stat195 stat196
## 1 -0.6644351 2.6270833 -1.1094601 -2.4200392 2.870713 -0.6590932
## 2 -0.6483142 1.4519118 -0.1963493 -2.3025322 1.255608 2.1617947
## 3 -1.5457382 -0.2977442 -1.7045015 0.7962404 -1.696063 -1.4771117
## 4 -1.1780495 -2.9747574 -1.1471518 -1.2377013 -1.010672 -2.6055975
## 5 2.8813178 -1.8964081 -1.2653487 -1.7839754 -2.872581 2.3033464
## 6 0.4437973 0.6599325 -1.4029555 -2.3118258 -1.792232 1.3934380
## stat197 stat198 stat199 stat200 stat201 stat202
## 1 -0.83056986 0.9550526 -1.7025776 -2.8263099 -0.7023998 0.2272806
## 2 -1.42178249 -1.2471864 2.5723093 -0.0233496 -1.8975239 1.9472262
## 3 -0.19233958 -0.5161456 0.0279946 -1.2333704 -2.9672263 -2.8666208
## 4 -1.23145902 1.4728470 -0.4562025 -2.2983441 -1.5101184 0.2530525
## 5 1.85018563 -1.8269292 -0.6337969 -2.1473246 0.9909850 1.0950903
## 6 -0.09311061 0.5144456 -2.8178268 -2.7555969 -2.3546004 -1.0558939
## stat203 stat204 stat205 stat206 stat207 stat208
## 1 1.166631220 0.007453276 2.9961641 1.5327307 -2.2293356 -0.9946009
## 2 -0.235396504 2.132749800 0.3707606 1.5604026 -1.0089217 2.1474257
## 3 0.003180946 2.229793310 2.7354040 0.8992231 2.9694967 2.3081024
## 4 -0.474482715 -1.584772230 -2.3224132 -0.9409741 -2.3179255 0.8032548
## 5 2.349412920 -1.276320220 -2.0203719 -1.1733509 1.0371852 -2.5086207
## 6 0.727436960 -0.960191786 -0.8964998 -1.6406623 -0.2330488 1.7993879
## stat209 stat210 stat211 stat212 stat213 stat214
## 1 -2.2182105 -1.4099774 -1.656754 2.6602585 -2.9270992 1.1240714
## 2 -2.8932488 -1.1641679 -2.605423 -1.5650513 2.9523673 2.0266318
## 3 -1.8279589 0.0472350 -2.026734 2.5054367 0.9903042 0.3274105
## 4 -1.0878067 0.1171303 2.645891 -1.6775225 1.3452160 1.4694063
## 5 -0.8158175 0.4060950 0.912256 0.2925677 2.1610141 0.5679936
## 6 -2.2664354 -0.2061083 -1.435174 2.6645632 0.4216259 -0.6419122
## stat215 stat216 stat217
## 1 -2.7510750 -0.5501796 1.2638469
## 2 2.8934650 -2.4099574 -1.2411407
## 3 -1.0947676 1.2852937 1.5411530
## 4 0.6343777 0.1345372 2.9102673
## 5 0.9908702 1.7909757 -2.0902610
## 6 -2.8113887 -1.0624912 0.2765074head(features.highprec)## JobName x1 x2 x3 x4 x5 x6
## 1 Job_00001 2.0734508 4.917267 19.96188 3.520878 7.861051 1.6067589
## 2 Job_00002 2.2682543 4.955773 19.11939 19.763031 6.931355 1.3622041
## 3 Job_00003 1.7424456 2.059819 13.37912 38.829132 6.274053 2.0529845
## 4 Job_00004 0.7873555 2.613983 17.23044 64.402557 5.377652 0.9067419
## 5 Job_00005 2.3342753 4.299076 14.64883 52.537304 6.793368 2.4605792
## 6 Job_00006 1.2365089 2.795370 11.13127 96.819939 6.583971 2.3510606
## x7 x8 x9 x10 x11 x12 x13
## 1 2.979479 8.537228 1.103368 4.6089458 1.050025e-07 7.995825 13.215498
## 2 2.388119 6.561461 0.588572 1.0283282 1.034518e-07 7.486966 22.557224
## 3 2.043592 10.275595 4.834385 4.3872848 1.062312e-07 6.350142 15.049810
## 4 2.395118 13.487331 3.340190 4.5053501 9.471887e-08 9.548698 17.170635
## 5 2.891535 9.362389 1.246039 1.7333300 1.010552e-07 9.596095 5.794567
## 6 1.247838 7.033354 1.852231 0.4839371 1.071662e-07 3.810983 23.863169
## x14 x15 x16 x17 x18 x19 x20
## 1 4.377983 0.2370623 6.075459 3.988347 4.767475 2.698775 1.035893
## 2 2.059315 0.5638121 6.903891 4.152054 6.849232 9.620731 1.915288
## 3 3.260057 2.0603445 8.424065 4.489893 3.493591 4.715386 1.558103
## 4 3.093478 1.8806034 11.189792 2.134271 5.588357 5.107871 1.489588
## 5 3.943076 1.5820830 7.096742 3.563378 7.765610 1.360272 1.240283
## 6 1.280562 1.1733382 7.062051 1.341864 7.748325 5.009365 1.725179
## x21 x22 x23 stat1 stat2 stat3 stat4
## 1 42.36548 1.356213 2.699796 2.3801832 0.1883335 -1.2284011 -0.5999233
## 2 26.63295 4.053961 2.375127 -1.4069480 1.8140973 1.6204884 2.6422672
## 3 20.09693 3.079888 4.488420 -0.7672566 -0.1230289 1.1415752 2.9805934
## 4 32.60415 1.355396 3.402398 0.4371202 -1.9355906 0.9028624 -1.6025400
## 5 44.58361 1.940301 2.249011 2.4492466 -0.6172000 -2.5520642 -2.1485929
## 6 28.75102 2.500499 5.563972 -1.7899084 1.8853619 2.4154840 -2.6022179
## stat5 stat6 stat7 stat8 stat9 stat10
## 1 0.148893163 -0.6622978 -2.4851868 0.3647782 2.5364335 2.92067981
## 2 1.920768980 1.7411555 -1.9599979 -2.0190558 -1.3732762 -0.31642506
## 3 2.422584300 -0.4166040 2.2205689 -2.6741531 0.4844292 2.73379230
## 4 -0.001795933 -0.6946563 -0.3693534 -0.9709467 1.7960306 0.74771154
## 5 -2.311132430 -1.0166832 2.7269876 1.5424492 -1.3156369 -0.09767897
## 6 -1.785491470 -1.8599915 1.4875095 2.0188572 -1.4892503 -1.41103566
## stat11 stat12 stat13 stat14 stat15 stat16
## 1 -2.3228905 -2.480567 -0.6335157 -0.3650149 -0.5322812 0.6029300
## 2 -0.8547903 1.119316 0.7227427 0.2121097 -0.1452281 -2.0361528
## 3 -2.1821580 2.865401 -2.9756081 2.9871745 1.9539525 -1.8857163
## 4 1.3982378 1.856765 -1.0379983 2.3341896 2.3057184 -2.8947697
## 5 0.9567220 2.567549 0.3184886 1.0307668 0.1644241 -0.6613821
## 6 0.5341771 -1.461822 0.4402476 -1.9282095 -0.3680157 1.8188807
## stat17 stat18 stat19 stat20 stat21 stat22
## 1 -1.04516208 2.3544915 2.4049001 0.2633883 -0.9788178 1.7868229
## 2 0.09513074 0.4727738 1.8899702 2.7892542 -1.3919091 -1.7198164
## 3 0.40285346 1.4655282 -1.4952788 2.9162340 -2.3893208 2.8161423
## 4 2.97446084 2.3896182 2.3083484 -1.1894441 -2.1982553 1.3666242
## 5 -0.98465055 0.6900643 1.5894209 -2.1204538 1.7961155 -0.9362189
## 6 -1.45726359 -2.1139548 -0.3964904 1.1764175 -2.9100556 -2.1359294
## stat23 stat24 stat25 stat26 stat27 stat28
## 1 -2.3718851 2.8580718 -0.4719713 -2.817086 -0.9518474 2.88892484
## 2 -2.3293245 1.5577759 -1.9569720 1.554194 -0.5081459 -1.58715141
## 3 -2.5402296 0.1422861 0.3572798 -1.051886 -2.1541717 0.03074004
## 4 -1.9679050 -1.4077642 2.5097435 1.683121 -0.2549745 -2.90384054
## 5 2.0523429 -2.2084844 -1.9280857 -2.116736 1.8180779 -1.42167580
## 6 0.2184991 -0.7599817 2.6880329 -2.903350 -1.0733233 -2.92416644
## stat29 stat30 stat31 stat32 stat33 stat34
## 1 0.7991088 -2.0059092 -0.2461502 0.6482101 -2.87462163 -0.3601543
## 2 1.9758110 -0.3874187 1.3566630 2.6493473 2.28463054 1.8591728
## 3 -0.4460218 1.0279679 1.3998452 -1.0183365 1.41109037 -2.4183984
## 4 1.0571996 2.5588036 -2.9830337 -1.1299983 0.05470414 -1.5566561
## 5 0.8854889 2.2774174 2.6499031 2.3053405 -2.39148426 -1.8272992
## 6 -0.8405267 0.1311945 0.4321289 -2.9622040 -2.55387473 2.6396458
## stat35 stat36 stat37 stat38 stat39 stat40
## 1 2.4286051 -0.5420244 -2.6782637 -2.8874269 -0.8945006 1.1749642
## 2 1.3709245 -1.3714181 1.3901204 1.2273489 -0.8934880 1.0540369
## 3 -0.9805572 2.0571353 0.8845031 2.0574493 1.1222047 1.8528618
## 4 1.0969149 -2.2820673 1.8852408 0.5391517 2.7334342 -0.4372566
## 5 -1.0971669 1.4867796 -2.3738465 -0.3743561 1.4266498 1.2551680
## 6 0.4584349 -2.2696617 -0.9935142 -0.5350499 -0.7874799 2.0009417
## stat41 stat42 stat43 stat44 stat45 stat46
## 1 -1.0474428 -1.3909023 2.54110503 -1.4320793 0.6298335 -2.09296608
## 2 2.5380247 1.6476108 0.44128850 -2.5049477 1.2726039 1.72492969
## 3 1.1477574 0.2288794 0.08891252 2.3044751 -0.7735722 -0.07302936
## 4 -1.3808300 -2.7900956 2.38297582 0.1686397 -2.1591296 1.60828602
## 5 0.2257536 1.9542116 2.66429019 0.8026123 -1.5521187 1.61751962
## 6 -1.3364114 -2.2898803 2.80735397 -0.8413086 1.0057797 -1.50653386
## stat47 stat48 stat49 stat50 stat51 stat52
## 1 -2.8318939 2.1445766 0.5668035 0.1544579 0.6291955 2.2197027
## 2 -0.5804687 -1.3689737 1.4908396 1.2465997 0.8896304 -2.6024318
## 3 0.7918019 1.5712964 1.1038082 -0.2545658 -2.1662638 0.2660159
## 4 -1.8894132 0.5680230 -0.7023218 -0.3972188 0.1578027 2.1770194
## 5 2.1088455 -2.7195437 2.1961412 -0.2615084 1.2109556 0.8260623
## 6 -1.4400891 -0.9421459 -1.7324599 -2.1720727 -2.8129435 0.6958785
## stat53 stat54 stat55 stat56 stat57 stat58
## 1 2.176805 0.5546907 -2.19704103 -0.2884173 1.3232913 -1.32824039
## 2 -2.107441 1.3864788 0.08781975 1.9998228 0.8014438 -0.26979154
## 3 1.234197 2.1337581 1.65231645 -0.4388691 -0.1811156 2.11277962
## 4 2.535406 -2.1387620 0.12856023 -1.9906180 0.9626449 1.65232646
## 5 -2.457080 2.1633499 0.60441124 2.5449364 -1.4978440 2.60542655
## 6 2.003033 -0.5379940 -2.19647264 -1.1954677 -0.5974466 -0.04703835
## stat59 stat60 stat61 stat62 stat63 stat64
## 1 1.24239659 -2.5798278 1.327928 1.68560362 0.6284891 -1.6798652
## 2 0.06379301 0.9465770 1.116928 0.03128772 -2.1944375 0.3382609
## 3 0.93223447 2.4597080 0.465251 -1.71033382 -0.5156728 1.8276784
## 4 -0.29840910 0.7273473 -2.313066 -1.47696018 2.5910559 -1.5127999
## 5 -1.17610002 -1.7948418 -2.669305 0.17813617 2.8956099 2.9411416
## 6 -1.01793981 0.2817057 2.228023 -0.86494124 -0.9747949 -0.1569053
## stat65 stat66 stat67 stat68 stat69 stat70
## 1 -2.9490898 -0.3325469 1.5745990 -2.2978280 1.5451891 -1.345990
## 2 -1.1174885 -1.5728682 -2.9229002 0.2658547 -1.9616533 2.506130
## 3 -0.2231264 -0.4503301 0.7932286 -1.2453773 -2.2309763 2.309761
## 4 -0.3522418 -2.0720532 0.9442933 2.9212906 0.5100371 -2.441108
## 5 -2.1648991 1.2002029 2.8266985 0.7461294 1.6772674 -1.280000
## 6 -2.2295458 1.1446493 0.2024925 -0.2983998 -2.8203752 1.224030
## stat71 stat72 stat73 stat74 stat75 stat76
## 1 1.0260956 2.1071210 2.6625669 -2.8924677 -0.02132523 -2.5058765
## 2 0.3525076 1.6922342 -1.2167022 -1.7271879 2.21176434 1.9329683
## 3 -2.1799035 -2.2645276 0.1415582 0.9887453 1.95592320 0.2951785
## 4 -2.4051409 2.0876484 -0.8632146 0.4011389 -1.16986716 -1.2391174
## 5 1.3538754 -0.8089395 -0.5122626 -2.1696892 1.07344925 2.6696169
## 6 -2.8073371 -1.4450488 0.5481212 -1.4381690 0.80917043 -0.1365944
## stat77 stat78 stat79 stat80 stat81 stat82
## 1 -2.5631845 -2.40331340 0.38416120 -1.2564875 -0.1550840 -1.1762617
## 2 -0.4462085 0.38400793 1.80483031 -0.8387642 0.7624431 0.9936900
## 3 1.6757870 -1.81900752 2.70904708 -0.3201959 2.5754235 1.6346260
## 4 -2.1012006 -2.24691081 1.78056848 1.0323739 1.0762523 2.1343851
## 5 -2.5736733 -1.99958372 -0.05388495 -2.5630073 -2.8783002 -0.5752426
## 6 1.6143972 0.03233746 2.90835762 1.4000487 2.9275615 -2.8503830
## stat83 stat84 stat85 stat86 stat87 stat88
## 1 1.2840565 -2.6794965 1.3956039 -1.5290235 2.221152 2.3794982
## 2 -0.2380048 1.9314318 -1.6747955 -0.3663656 1.582659 -0.5222489
## 3 -0.9150769 -1.5520337 2.4186287 2.7273662 1.306642 0.1320062
## 4 -2.5824408 -2.7775943 0.5085060 0.4689015 2.053348 0.7957955
## 5 -1.0017741 -0.2009138 0.3770109 2.4335201 -1.118058 1.3953410
## 6 2.4891765 2.9931953 -1.4171852 0.3905659 -1.856119 -2.1690490
## stat89 stat90 stat91 stat92 stat93 stat94
## 1 -0.9885110 -0.8873261 -2.7810929 -1.53325891 2.6002395 1.8890998
## 2 0.9982028 -1.2382015 -0.1574496 0.41086048 -0.5412626 -0.2421387
## 3 0.5956759 1.6871066 2.2452753 2.74279594 -1.5860478 2.9393122
## 4 2.0902634 2.1752586 -2.0677712 -2.37861037 1.1653302 0.1500632
## 5 2.9820614 0.8111660 -0.7842287 0.03766387 -1.1681970 2.1217251
## 6 -1.7428021 0.1579032 1.7456742 -0.36858466 -0.1304616 -1.4555819
## stat95 stat96 stat97 stat98 stat99 stat100
## 1 -2.6056035 -0.5814857 2.57652426 -2.3297751 2.6324007 1.445827
## 2 -2.0271583 -0.9126074 2.49582648 0.9745382 1.1339203 -2.549544
## 3 0.3823181 -0.6324139 2.46221566 1.1151560 0.4624891 0.107072
## 4 2.6414623 -0.6630505 2.10394859 1.2627635 0.4861740 1.697012
## 5 1.4642254 2.6485956 -0.07699547 0.6219473 -1.8815142 -2.685463
## 6 1.8937331 -0.4690555 1.04671776 -0.5879866 -0.9766789 2.405940
## stat101 stat102 stat103 stat104 stat105 stat106
## 1 -2.1158021 2.603936 1.7745128 -1.8903574 -1.8558655 1.0122044
## 2 -2.7998588 -2.267895 0.5336456 -0.2859477 -0.5196246 -0.9417582
## 3 0.7969509 -1.744906 -0.7960327 1.9767258 -0.2007264 -0.7872376
## 4 1.7071959 -1.540221 1.6770362 1.5395796 -0.4855365 -1.2894115
## 5 -1.4627420 -1.700983 2.4376490 0.2731541 1.5275587 1.3256483
## 6 2.6888530 1.090155 2.0769854 1.9615480 1.8689761 2.8975825
## stat107 stat108 stat109 stat110 stat111 stat112
## 1 1.954508 -0.3376471 2.503084 0.3099165 2.7209847 -2.3911204
## 2 -2.515160 0.3998704 -1.077093 2.4228268 -0.7759693 0.2513882
## 3 1.888827 1.5819857 -2.066659 -2.0008364 0.6997684 2.6157095
## 4 1.076395 -1.8524148 -2.689204 1.0985872 1.2389493 2.1018629
## 5 2.828866 -1.8590252 -2.424163 1.4391942 -0.6173239 -1.5218846
## 6 -1.419639 0.7888914 1.996463 0.9813507 0.9034198 1.3810679
## stat113 stat114 stat115 stat116 stat117 stat118
## 1 -1.616161 1.0878664 0.9860094 -0.06288462 -1.013501 -1.2212842
## 2 -1.554771 1.8683100 0.4880588 -0.63865489 -1.610217 -1.7713343
## 3 -2.679801 -2.9486952 1.7753417 0.90311784 -1.318836 -0.1429040
## 4 2.459229 -0.5584171 0.4419581 -0.09586351 0.595442 0.2883342
## 5 -2.102200 1.6300170 -2.3498287 1.36771894 -1.912202 -0.2563821
## 6 -1.835037 0.6577786 -2.9928374 2.13540316 -1.437299 -0.9570006
## stat119 stat120 stat121 stat122 stat123 stat124
## 1 2.9222729 1.9151262 1.6686068 2.0061224 1.5723072 0.78819227
## 2 2.1828208 0.8283178 -2.4458632 1.7133740 1.1393738 -0.07182054
## 3 0.9721319 1.2723130 2.8002086 2.7670381 -2.2252586 2.17499113
## 4 -1.9327896 -2.5369370 1.7835028 1.0262097 -1.8790983 -0.43639564
## 5 1.3230809 -2.8145256 -0.9547533 -2.0435417 -0.2758764 -1.85668027
## 6 0.1720700 -1.4568460 1.4115051 -0.9878145 2.3895061 -2.33730745
## stat125 stat126 stat127 stat128 stat129 stat130
## 1 1.588372 1.1620011 -0.2474264 1.650328 2.5147598 0.37283245
## 2 -1.173771 0.8162020 0.3510315 -1.263667 1.7245284 -0.72852904
## 3 -1.503497 -0.5656394 2.8040256 -2.139287 -1.7221642 2.17899609
## 4 1.040967 -2.9039600 0.3103742 1.462339 -1.2940350 -2.95015502
## 5 -2.866184 1.6885070 -2.2525666 -2.628631 1.8581577 2.80127025
## 6 -1.355111 1.5017927 0.4295921 -0.580415 0.9851009 -0.03773117
## stat131 stat132 stat133 stat134 stat135 stat136
## 1 -0.09028241 0.5194538 2.8478346 2.6664724 -2.0206311 1.398415090
## 2 -0.53045595 1.4134049 2.9180586 0.3299096 1.4784122 -1.278896090
## 3 1.35843194 0.2279946 0.3532595 0.6138676 -0.3443284 0.057763811
## 4 -1.92450273 1.2698178 -1.5299660 -2.6083462 1.1665530 -0.187791914
## 5 1.49036849 2.6337729 -2.3206244 0.4978287 -1.7397571 0.001200184
## 6 -0.64642709 -1.9256228 1.7032650 -0.9152725 -0.3188055 2.155395980
## stat137 stat138 stat139 stat140 stat141 stat142
## 1 -1.2794871 0.4064890 -0.4539998 2.6660173 -1.8375313 0.4711883
## 2 -2.7709017 -1.6303773 -1.9025910 0.2572918 0.6612002 1.4764348
## 3 -1.1930757 -0.1051243 -0.5108380 -1.0879666 2.4969513 -0.9477230
## 4 -1.2318919 2.2348571 0.1788580 -1.5851788 -1.2384283 -2.1859181
## 5 1.8685058 2.7229517 -2.9077182 2.6606939 -1.5963592 -2.2213492
## 6 -0.4807318 -1.2117369 -0.9358531 -2.5100758 -2.3803916 -0.7096854
## stat143 stat144 stat145 stat146 stat147 stat148
## 1 1.9466263 2.2689433 -0.3597288 -0.6551386 1.65438592 0.6404466
## 2 1.3156421 2.4459090 -0.3790028 1.4858465 -0.07784461 1.0096149
## 3 0.1959563 2.3062942 1.8459278 2.6848175 -2.70935774 -1.2093409
## 4 1.7633296 -2.8171508 2.0902622 -2.6625464 -1.12600601 -2.1926479
## 5 0.3885758 1.8160636 2.8257299 -1.4526173 1.60679603 2.3807991
## 6 0.7623450 0.2692145 -2.4307463 -2.1244523 -2.67803812 -1.5273387
## stat149 stat150 stat151 stat152 stat153 stat154
## 1 0.1583575 0.4755351 0.3213410 2.0241520 1.5720103 -0.1825875
## 2 -0.4311406 2.9577663 0.6937252 0.1397280 0.3775735 -1.1012636
## 3 -0.8352824 2.5716205 1.7528236 0.4326277 -2.2334397 -2.6265771
## 4 -2.8069143 1.8813509 2.3358023 0.1015632 1.2117474 -1.3714278
## 5 -1.6166265 1.1112266 -1.1998471 2.9316769 -2.1676455 -0.3411089
## 6 -0.2265472 2.7264354 -1.6746094 -2.3376281 -1.7022788 -1.2352397
## stat155 stat156 stat157 stat158 stat159 stat160
## 1 -1.139657 0.07061254 0.5893906 -1.9920996 -2.83714366 2.249398
## 2 -2.041093 0.74047768 2.5415072 -1.2697256 -1.64364433 -2.448922
## 3 -1.219507 -0.55198693 0.4046920 1.2098547 -0.90412390 -1.934093
## 4 2.992191 2.33222485 2.0622969 -0.6714653 2.76836085 -1.431120
## 5 -2.362356 -1.23906672 0.4746319 -0.7849202 0.69399995 2.052411
## 6 -1.604499 1.31051409 -0.5164744 0.6288667 0.07899523 -2.287402
## stat161 stat162 stat163 stat164 stat165 stat166
## 1 1.7182635 -1.2323593 2.7350423 1.0707235 1.1621544 0.9493989
## 2 -0.6247674 2.6740098 2.8211024 1.5561292 -1.1027147 1.0519739
## 3 -0.6230453 -0.7993517 -2.8318374 -1.1148673 1.4261659 0.5294309
## 4 1.7644744 0.1696584 1.2653207 0.6621516 0.9470508 0.1985014
## 5 -1.2070210 0.7243784 0.9736322 2.7426259 -2.6862383 1.6840212
## 6 2.3705316 -2.1667893 -0.2516685 -0.8425958 -1.9099342 -2.8607297
## stat167 stat168 stat169 stat170 stat171 stat172
## 1 0.1146510 2.3872008 1.1180918 -0.95370555 -2.25076509 0.2348182
## 2 1.0760417 -2.0449336 0.9715676 -0.40173489 -0.11953555 -2.3107369
## 3 1.1735898 1.3860190 -2.2894719 0.06350347 0.29191551 -1.6079744
## 4 2.5511832 0.5446648 1.2694012 -0.84571201 0.79789722 0.2623538
## 5 2.2900002 2.6289782 -0.2783571 1.39032829 -0.55532032 1.0499046
## 6 -0.7513983 2.9617066 -2.2119520 -1.71958113 -0.01452018 -0.2751517
## stat173 stat174 stat175 stat176 stat177 stat178
## 1 1.79366076 -1.920206 -0.38841942 0.8530301 1.64532077 -1.1354179
## 2 -0.07484659 1.337846 2.20911694 0.9616837 -2.80810070 -2.1136749
## 3 -1.05521810 -1.483741 0.06148359 2.3066039 -0.34688616 1.1840581
## 4 0.31460321 1.195741 2.97633862 1.1685091 -0.06346265 1.4205489
## 5 -1.39428365 2.458523 0.64836472 -1.0396386 -0.57828104 -0.5006818
## 6 2.31844401 1.239864 -2.06490874 0.7696204 -1.77586019 2.0855925
## stat179 stat180 stat181 stat182 stat183 stat184
## 1 2.0018647 0.1476815 -1.27279520 1.9181504 -0.5297624 -2.9718938
## 2 -2.1351449 2.9012582 -1.09914911 -2.5488517 -2.8377736 1.4073374
## 3 -1.7819908 2.9902627 0.81908613 0.2503852 0.3712984 -2.1714024
## 4 -0.1026974 -2.4763253 -2.52645421 1.3096315 2.1458161 -1.5228094
## 5 -2.2298794 2.4465680 -0.70346898 -1.6997617 2.9178164 -0.3615532
## 6 -1.1168108 1.5552123 -0.01361342 1.7338791 -1.1104763 0.1882416
## stat185 stat186 stat187 stat188 stat189 stat190
## 1 -0.1043832 -1.5047463 2.700351 -2.4780862 -1.9078265 0.9978108
## 2 -2.0310574 -0.5380074 -1.963275 -1.2221278 -2.4290681 -1.9515115
## 3 2.6727278 1.2688179 -1.399018 -2.9612138 2.6456394 2.0073323
## 4 -2.7796295 2.0682354 2.243727 0.4296881 0.1931333 2.2710960
## 5 -0.6231265 2.5833981 2.229041 0.8139584 1.4544131 1.8886451
## 6 2.7204690 -2.4469144 -1.421998 1.7477882 -0.1481806 0.6011560
## stat191 stat192 stat193 stat194 stat195 stat196
## 1 -0.6644351 2.6270833 -1.1094601 -2.4200392 2.870713 -0.6590932
## 2 -0.6483142 1.4519118 -0.1963493 -2.3025322 1.255608 2.1617947
## 3 -1.5457382 -0.2977442 -1.7045015 0.7962404 -1.696063 -1.4771117
## 4 -1.1780495 -2.9747574 -1.1471518 -1.2377013 -1.010672 -2.6055975
## 5 2.8813178 -1.8964081 -1.2653487 -1.7839754 -2.872581 2.3033464
## 6 0.4437973 0.6599325 -1.4029555 -2.3118258 -1.792232 1.3934380
## stat197 stat198 stat199 stat200 stat201 stat202
## 1 -0.83056986 0.9550526 -1.7025776 -2.8263099 -0.7023998 0.2272806
## 2 -1.42178249 -1.2471864 2.5723093 -0.0233496 -1.8975239 1.9472262
## 3 -0.19233958 -0.5161456 0.0279946 -1.2333704 -2.9672263 -2.8666208
## 4 -1.23145902 1.4728470 -0.4562025 -2.2983441 -1.5101184 0.2530525
## 5 1.85018563 -1.8269292 -0.6337969 -2.1473246 0.9909850 1.0950903
## 6 -0.09311061 0.5144456 -2.8178268 -2.7555969 -2.3546004 -1.0558939
## stat203 stat204 stat205 stat206 stat207 stat208
## 1 1.166631220 0.007453276 2.9961641 1.5327307 -2.2293356 -0.9946009
## 2 -0.235396504 2.132749800 0.3707606 1.5604026 -1.0089217 2.1474257
## 3 0.003180946 2.229793310 2.7354040 0.8992231 2.9694967 2.3081024
## 4 -0.474482715 -1.584772230 -2.3224132 -0.9409741 -2.3179255 0.8032548
## 5 2.349412920 -1.276320220 -2.0203719 -1.1733509 1.0371852 -2.5086207
## 6 0.727436960 -0.960191786 -0.8964998 -1.6406623 -0.2330488 1.7993879
## stat209 stat210 stat211 stat212 stat213 stat214
## 1 -2.2182105 -1.4099774 -1.656754 2.6602585 -2.9270992 1.1240714
## 2 -2.8932488 -1.1641679 -2.605423 -1.5650513 2.9523673 2.0266318
## 3 -1.8279589 0.0472350 -2.026734 2.5054367 0.9903042 0.3274105
## 4 -1.0878067 0.1171303 2.645891 -1.6775225 1.3452160 1.4694063
## 5 -0.8158175 0.4060950 0.912256 0.2925677 2.1610141 0.5679936
## 6 -2.2664354 -0.2061083 -1.435174 2.6645632 0.4216259 -0.6419122
## stat215 stat216 stat217
## 1 -2.7510750 -0.5501796 1.2638469
## 2 2.8934650 -2.4099574 -1.2411407
## 3 -1.0947676 1.2852937 1.5411530
## 4 0.6343777 0.1345372 2.9102673
## 5 0.9908702 1.7909757 -2.0902610
## 6 -2.8113887 -1.0624912 0.2765074features = features.highprec
#str(features) Checking correlations to evaluate removal of redundant features
corr.matrix = round(cor(features[sapply(features, is.numeric)]),2)
# filter out only highly correlated variables
threshold = 0.6
corr.matrix.tmp = corr.matrix
diag(corr.matrix.tmp) = 0
high.corr = apply(abs(corr.matrix.tmp) >= threshold, 1, any)
high.corr.matrix = corr.matrix.tmp[high.corr, high.corr]
DT::datatable(corr.matrix)DT::datatable(high.corr.matrix)Feature Names
feature.names = colnames(features)
drops <- c('JobName')
feature.names = feature.names[!(feature.names %in% drops)]
#str(feature.names)Read and Clean Labels
labels = read.csv("../../Data/labels.csv")
#str(labels)
labels = labels[,c("JobName", output.var)]
summary(labels)## JobName y3
## Job_00001: 1 Min. : 95.91
## Job_00002: 1 1st Qu.:118.21
## Job_00003: 1 Median :123.99
## Job_00004: 1 Mean :125.36
## Job_00005: 1 3rd Qu.:131.06
## Job_00006: 1 Max. :193.73
## (Other) :9994 NA's :2497Merge Datasets
data <- merge(features, labels, by = 'JobName')
drops <- c('JobName')
data = data[,(!colnames(data) %in% drops)]
#str(data)Transformations
if (transform.abs == TRUE){
data[,label.names] = 10^(data[,label.names]/20)
data = filter(data, y3 < 1E7)
}
#str(data)
if (log.pred == TRUE){
data[label.names] = log(data[alt.scale.label.name],10)
drops = c(alt.scale.label.name)
data = data[!(names(data) %in% drops)]
}
#str(data)Remove NA Cases
data = data[complete.cases(data),]Exploratory Data Analysis
Check correlation of Label with Featires
if (eda == TRUE){
corr.to.label =round(cor(dplyr::select(data,-one_of(label.names)),dplyr::select_at(data,label.names)),4)
DT::datatable(corr.to.label)
}Multicollinearity - VIF
if (eda == TRUE){
vifDF = usdm::vif(select_at(data,feature.names)) %>% arrange(desc(VIF))
head(vifDF,10)
}## Variables VIF
## 1 stat131 1.065226
## 2 stat113 1.063307
## 3 stat202 1.062843
## 4 stat72 1.062697
## 5 stat142 1.062557
## 6 stat31 1.060336
## 7 stat80 1.059814
## 8 stat147 1.059225
## 9 stat140 1.059145
## 10 stat8 1.059094Scatterplots
panel.hist <- function(x, ...)
{
usr <- par("usr"); on.exit(par(usr))
par(usr = c(usr[1:2], 0, 1.5) )
h <- hist(x, plot = FALSE)
breaks <- h$breaks; nB <- length(breaks)
y <- h$counts; y <- y/max(y)
rect(breaks[-nB], 0, breaks[-1], y, col = "cyan", ...)
}if (eda == TRUE){
histogram(data[ ,label.names])
#hist(data[complete.cases(data),alt.scale.label.name])
}
# https://stackoverflow.com/questions/24648729/plot-one-numeric-variable-against-n-numeric-variables-in-n-plots
ind.pairs.plot <- function(data, xvars=NULL, yvar)
{
df <- data
if (is.null(xvars)) {
xvars = names(data[which(names(data)!=yvar)])
}
#choose a format to display charts
ncharts <- length(xvars)
for(i in 1:ncharts){
plot(df[,xvars[i]],df[,yvar], xlab = xvars[i], ylab = yvar)
}
}
if (eda == TRUE){
ind.pairs.plot(data, feature.names, label.names)
}
#
# pl <- ggplot(data, aes(x=x18, y = y3))
# pl2 <- pl + geom_point(aes(alpha = 0.1)) # default color gradient based on 'hp'
# print(pl2)Feature Engineering
if(eda ==FALSE){
# x18 may need transformations
plot(data[,'x18'], data[,label.names], main = "Original Scatter Plot vs. x18", ylab = label.names, xlab = 'x18')
plot(sqrt(data[,'x18']), data[,label.names], main = "Original Scatter Plot vs. sqrt(x18)", ylab = label.names, xlab = 'sqrt(x18)')
# transforming x18
data$sqrt.x18 = sqrt(data$x18)
data = dplyr::select(data,-one_of('x18'))
# what about x7, x9?
# x11 looks like data is at discrete points after a while. Will this be a problem?
}Modeling
Train Test Split
data = data[sample(nrow(data)),] # randomly shuffle data
split = sample.split(data[,label.names], SplitRatio = 0.8)
data.train = subset(data, split == TRUE)
data.test = subset(data, split == FALSE)Common Functions
plot.diagnostics <- function(model, train) {
plot(model)
residuals = resid(model) # Plotted above in plot(lm.out)
r.standard = rstandard(model)
r.student = rstudent(model)
plot(predict(model,train),r.student,
ylab="Student Residuals", xlab="Predicted Values",
main="Student Residual Plot")
abline(0, 0)
plot(predict(model, train),r.standard,
ylab="Standard Residuals", xlab="Predicted Values",
main="Standard Residual Plot")
abline(0, 0)
abline(2, 0)
abline(-2, 0)
# Histogram
hist(r.student, freq=FALSE, main="Distribution of Studentized Residuals",
xlab="Studentized Residuals", ylab="Density", ylim=c(0,0.5))
# Create range of x-values for normal curve
xfit <- seq(min(r.student)-1, max(r.student)+1, length=40)
# Generate values from the normal distribution at the specified values
yfit <- (dnorm(xfit))
# Add the normal curve
lines(xfit, yfit, ylim=c(0,0.5))
# http://www.stat.columbia.edu/~martin/W2024/R7.pdf
# Influential plots
inf.meas = influence.measures(model)
# print (summary(inf.meas)) # too much data
# Leverage plot
lev = hat(model.matrix(model))
plot(lev, ylab = 'Leverage - check')
# Cook's Distance
cd = cooks.distance(model)
plot(cd,ylab="Cooks distances")
abline(4/nrow(train),0)
abline(1,0)
print (paste("Number of data points that have Cook's D > 4/n: ", length(cd[cd > 4/nrow(train)]), sep = ""))
print (paste("Number of data points that have Cook's D > 1: ", length(cd[cd > 1]), sep = ""))
return(cd)
}
train.caret.glmselect = function(formula, data, method
,subopt = NULL, feature.names
, train.control = NULL, tune.grid = NULL, pre.proc = NULL){
if(is.null(train.control)){
train.control <- trainControl(method = "cv"
,number = 10
,search = "grid"
,verboseIter = TRUE
,allowParallel = TRUE
)
}
if(is.null(tune.grid)){
if (method == 'leapForward' | method == 'leapBackward' | method == 'leapSeq'){
tune.grid = data.frame(nvmax = 1:length(feature.names))
}
if (method == 'glmnet' && subopt == 'LASSO'){
# Will only show 1 Lambda value during training, but that is OK
# https://stackoverflow.com/questions/47526544/why-need-to-tune-lambda-with-carettrain-method-glmnet-and-cv-glmnet
# Another option for LASSO is this: https://github.com/topepo/caret/blob/master/RegressionTests/Code/lasso.R
lambda = 10^seq(-2,0, length =100)
alpha = c(1)
tune.grid = expand.grid(alpha = alpha,lambda = lambda)
}
if (method == 'lars'){
# https://github.com/topepo/caret/blob/master/RegressionTests/Code/lars.R
fraction = seq(0, 1, length = 100)
tune.grid = expand.grid(fraction = fraction)
pre.proc = c("center", "scale")
}
}
# http://sshaikh.org/2015/05/06/parallelize-machine-learning-in-r-with-multi-core-cpus/
cl <- makeCluster(detectCores()*0.75) # use 75% of cores only, leave rest for other tasks
registerDoParallel(cl)
set.seed(1)
# note that the seed has to actually be set just before this function is called
# settign is above just not ensure reproducibility for some reason
model.caret <- caret::train(formula
, data = data
, method = method
, tuneGrid = tune.grid
, trControl = train.control
, preProc = pre.proc
)
stopCluster(cl)
registerDoSEQ() # register sequential engine in case you are not using this function anymore
if (method == 'leapForward' | method == 'leapBackward' | method == 'leapSeq'){
print(model.caret$results) # all model results
print(model.caret$bestTune) # best model
model = model.caret$finalModel
# Provides the coefficients of the best model
id = rownames(model.caret$bestTune)
message("Coefficients of final model:")
print (coef(model, id = id))
# Need to find alternate to plotting diagnostic plots
# plot.diagnostics(model.forward,data.train)
# plot(model.forward,labels = colnames(data.train),scale=c("bic")) ## too many variables
return(list(model = model,id = id))
}
if (method == 'glmnet' && subopt == 'LASSO'){
print(model.caret)
print(plot(model.caret))
print(model.caret$bestTune)
id = NULL # not really needed but added for consistency
return(list(model = model.caret,id = id))
}
if (method == 'lars'){
print(model.caret)
print(plot(model.caret))
print(model.caret$bestTune)
id = NULL # not really needed but added for consistency
return(list(model = model.caret,id = id))
}
}
# https://stackoverflow.com/questions/48265743/linear-model-subset-selection-goodness-of-fit-with-k-fold-cross-validation
# changes slightly since call[[2]] was just returning "formula" without actually returnign the value in formula
predict.regsubsets <- function(object, newdata, id, formula, ...) {
#form <- as.formula(object$call[[2]])
mat <- model.matrix(formula, newdata) # adds intercept and expands any interaction terms
coefi <- coef(object, id = id)
xvars <- names(coefi)
return(mat[,xvars]%*%coefi)
}
test.model = function(model, test, level=0.95
,draw.limits = FALSE, good = 0.1, ok = 0.15
,method = NULL, subopt = NULL
,id = NULL, formula, feature.names, label.names){
## if using caret for glm select equivalent functionality,
## need to set regsubset = TRUE, pass id of best model through id variable,
## and pass formula (full is ok as it will select subset of variables from there)
if (is.null(method)){
pred = predict(model, newdata=test, interval="confidence", level = level)
}
if (method == 'leapForward' | method == 'leapBackward' | method == 'leapSeq'){
pred = predict.regsubsets(model, newdata = test, id = id, formula = formula)
}
if (method == 'glmnet' && subopt == 'LASSO'){
xtest = as.matrix(test[,feature.names])
pred=as.data.frame(predict(model, xtest))
}
if (method == 'lars'){
pred=as.data.frame(predict(model, newdata = test))
}
# Summary of predicted values
print ("Summary of predicted values: ")
print(summary(pred[,1]))
test.mse = mean((test[,label.names]-pred[,1])^2)
print (paste(method, subopt, "Test MSE:", test.mse, sep=" "))
plot(test[,label.names],pred[,1],xlab = "Actual", ylab = "Predicted")
abline(0,(1+good),col='green', lwd = 3)
abline(0,(1-good),col='green', lwd = 3)
abline(0,(1+ok),col='blue', lwd = 3)
abline(0,(1-ok),col='blue', lwd = 3)
}Setup Formulae
n <- names(data.train)
formula <- as.formula(paste(paste(n[n %in% label.names], collapse = " + ")," ~", paste(n[!n %in% label.names], collapse = " + ")))
grand.mean.formula = as.formula(paste(paste(n[n %in% label.names], collapse = " + ")," ~ 1"))
print(formula)## y3 ~ x1 + x2 + x3 + x4 + x5 + x6 + x7 + x8 + x9 + x10 + x11 +
## x12 + x13 + x14 + x15 + x16 + x17 + x18 + x19 + x20 + x21 +
## x22 + x23 + stat1 + stat2 + stat3 + stat4 + stat5 + stat6 +
## stat7 + stat8 + stat9 + stat10 + stat11 + stat12 + stat13 +
## stat14 + stat15 + stat16 + stat17 + stat18 + stat19 + stat20 +
## stat21 + stat22 + stat23 + stat24 + stat25 + stat26 + stat27 +
## stat28 + stat29 + stat30 + stat31 + stat32 + stat33 + stat34 +
## stat35 + stat36 + stat37 + stat38 + stat39 + stat40 + stat41 +
## stat42 + stat43 + stat44 + stat45 + stat46 + stat47 + stat48 +
## stat49 + stat50 + stat51 + stat52 + stat53 + stat54 + stat55 +
## stat56 + stat57 + stat58 + stat59 + stat60 + stat61 + stat62 +
## stat63 + stat64 + stat65 + stat66 + stat67 + stat68 + stat69 +
## stat70 + stat71 + stat72 + stat73 + stat74 + stat75 + stat76 +
## stat77 + stat78 + stat79 + stat80 + stat81 + stat82 + stat83 +
## stat84 + stat85 + stat86 + stat87 + stat88 + stat89 + stat90 +
## stat91 + stat92 + stat93 + stat94 + stat95 + stat96 + stat97 +
## stat98 + stat99 + stat100 + stat101 + stat102 + stat103 +
## stat104 + stat105 + stat106 + stat107 + stat108 + stat109 +
## stat110 + stat111 + stat112 + stat113 + stat114 + stat115 +
## stat116 + stat117 + stat118 + stat119 + stat120 + stat121 +
## stat122 + stat123 + stat124 + stat125 + stat126 + stat127 +
## stat128 + stat129 + stat130 + stat131 + stat132 + stat133 +
## stat134 + stat135 + stat136 + stat137 + stat138 + stat139 +
## stat140 + stat141 + stat142 + stat143 + stat144 + stat145 +
## stat146 + stat147 + stat148 + stat149 + stat150 + stat151 +
## stat152 + stat153 + stat154 + stat155 + stat156 + stat157 +
## stat158 + stat159 + stat160 + stat161 + stat162 + stat163 +
## stat164 + stat165 + stat166 + stat167 + stat168 + stat169 +
## stat170 + stat171 + stat172 + stat173 + stat174 + stat175 +
## stat176 + stat177 + stat178 + stat179 + stat180 + stat181 +
## stat182 + stat183 + stat184 + stat185 + stat186 + stat187 +
## stat188 + stat189 + stat190 + stat191 + stat192 + stat193 +
## stat194 + stat195 + stat196 + stat197 + stat198 + stat199 +
## stat200 + stat201 + stat202 + stat203 + stat204 + stat205 +
## stat206 + stat207 + stat208 + stat209 + stat210 + stat211 +
## stat212 + stat213 + stat214 + stat215 + stat216 + stat217print(grand.mean.formula)## y3 ~ 1# Update feature.names because we may have transformed some features
feature.names = n[!n %in% label.names]Full & Grand Means Model
model.full = lm(formula , data.train)
summary(model.full)##
## Call:
## lm(formula = formula, data = data.train)
##
## Residuals:
## Min 1Q Median 3Q Max
## -22.324 -6.160 -1.630 4.611 56.277
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.464e+01 2.777e+00 34.073 < 2e-16 ***
## x1 -3.514e-02 1.934e-01 -0.182 0.855797
## x2 1.521e-01 1.239e-01 1.228 0.219683
## x3 3.693e-02 3.395e-02 1.088 0.276667
## x4 -1.355e-02 2.671e-03 -5.073 4.03e-07 ***
## x5 1.785e-01 8.750e-02 2.040 0.041435 *
## x6 2.585e-03 1.762e-01 0.015 0.988295
## x7 3.303e+00 1.885e-01 17.519 < 2e-16 ***
## x8 1.587e-01 4.400e-02 3.607 0.000312 ***
## x9 9.056e-01 9.865e-02 9.180 < 2e-16 ***
## x10 3.369e-01 9.178e-02 3.670 0.000244 ***
## x11 5.872e+07 2.192e+07 2.680 0.007394 **
## x12 -4.622e-02 5.571e-02 -0.830 0.406755
## x13 2.457e-02 2.218e-02 1.108 0.267863
## x14 -1.984e-01 9.574e-02 -2.072 0.038304 *
## x15 2.699e-02 9.096e-02 0.297 0.766654
## x16 2.459e-01 6.304e-02 3.901 9.68e-05 ***
## x17 4.087e-01 9.613e-02 4.251 2.16e-05 ***
## x18 1.683e+00 6.732e-02 25.005 < 2e-16 ***
## x19 7.622e-02 4.890e-02 1.559 0.119160
## x20 1.642e-01 3.401e-01 0.483 0.629125
## x21 4.054e-02 1.252e-02 3.237 0.001214 **
## x22 -1.450e-01 1.028e-01 -1.411 0.158289
## x23 3.588e-03 9.673e-02 0.037 0.970415
## stat1 2.077e-02 7.353e-02 0.282 0.777644
## stat2 -1.798e-02 7.354e-02 -0.244 0.806883
## stat3 1.738e-01 7.345e-02 2.366 0.018006 *
## stat4 -9.330e-02 7.364e-02 -1.267 0.205231
## stat5 -1.707e-03 7.351e-02 -0.023 0.981477
## stat6 -1.337e-03 7.392e-02 -0.018 0.985572
## stat7 -2.630e-02 7.348e-02 -0.358 0.720393
## stat8 4.434e-03 7.370e-02 0.060 0.952023
## stat9 -4.175e-02 7.346e-02 -0.568 0.569815
## stat10 -7.659e-02 7.371e-02 -1.039 0.298814
## stat11 -9.635e-02 7.404e-02 -1.301 0.193245
## stat12 4.989e-02 7.322e-02 0.681 0.495697
## stat13 -1.318e-01 7.321e-02 -1.800 0.071850 .
## stat14 -2.966e-01 7.314e-02 -4.055 5.08e-05 ***
## stat15 -4.843e-02 7.304e-02 -0.663 0.507365
## stat16 4.115e-02 7.358e-02 0.559 0.575990
## stat17 -1.786e-02 7.306e-02 -0.244 0.806862
## stat18 -6.868e-02 7.303e-02 -0.940 0.347013
## stat19 6.293e-02 7.319e-02 0.860 0.389899
## stat20 -1.045e-01 7.295e-02 -1.433 0.151889
## stat21 -8.647e-03 7.393e-02 -0.117 0.906883
## stat22 -7.656e-02 7.329e-02 -1.045 0.296212
## stat23 1.893e-01 7.310e-02 2.589 0.009650 **
## stat24 -1.025e-01 7.352e-02 -1.394 0.163472
## stat25 -1.338e-01 7.333e-02 -1.825 0.068121 .
## stat26 -7.923e-02 7.337e-02 -1.080 0.280274
## stat27 1.025e-01 7.344e-02 1.396 0.162865
## stat28 4.467e-02 7.384e-02 0.605 0.545246
## stat29 7.528e-02 7.399e-02 1.017 0.308980
## stat30 8.061e-02 7.409e-02 1.088 0.276634
## stat31 -2.678e-02 7.421e-02 -0.361 0.718246
## stat32 9.231e-04 7.410e-02 0.012 0.990061
## stat33 -1.255e-01 7.315e-02 -1.715 0.086333 .
## stat34 7.594e-02 7.359e-02 1.032 0.302142
## stat35 -1.595e-01 7.358e-02 -2.168 0.030182 *
## stat36 3.637e-02 7.284e-02 0.499 0.617565
## stat37 -1.068e-01 7.397e-02 -1.444 0.148902
## stat38 1.143e-01 7.377e-02 1.549 0.121483
## stat39 -2.184e-02 7.304e-02 -0.299 0.764909
## stat40 -3.365e-02 7.337e-02 -0.459 0.646567
## stat41 -1.953e-01 7.326e-02 -2.666 0.007692 **
## stat42 -7.526e-02 7.361e-02 -1.022 0.306620
## stat43 -7.189e-02 7.344e-02 -0.979 0.327684
## stat44 3.912e-02 7.353e-02 0.532 0.594714
## stat45 -1.307e-01 7.339e-02 -1.781 0.074906 .
## stat46 7.951e-02 7.378e-02 1.078 0.281220
## stat47 2.969e-02 7.422e-02 0.400 0.689140
## stat48 4.386e-02 7.360e-02 0.596 0.551200
## stat49 7.005e-02 7.311e-02 0.958 0.337997
## stat50 4.491e-02 7.286e-02 0.616 0.537615
## stat51 6.669e-02 7.354e-02 0.907 0.364553
## stat52 1.284e-02 7.344e-02 0.175 0.861259
## stat53 -1.829e-02 7.379e-02 -0.248 0.804209
## stat54 -1.270e-01 7.415e-02 -1.712 0.086943 .
## stat55 8.737e-02 7.319e-02 1.194 0.232611
## stat56 -4.779e-02 7.367e-02 -0.649 0.516547
## stat57 -1.705e-02 7.292e-02 -0.234 0.815096
## stat58 -1.597e-03 7.266e-02 -0.022 0.982461
## stat59 8.355e-02 7.350e-02 1.137 0.255673
## stat60 1.489e-01 7.393e-02 2.015 0.044001 *
## stat61 -9.188e-02 7.370e-02 -1.247 0.212567
## stat62 -3.451e-02 7.350e-02 -0.470 0.638681
## stat63 6.928e-02 7.363e-02 0.941 0.346787
## stat64 -6.422e-02 7.332e-02 -0.876 0.381128
## stat65 -5.599e-02 7.382e-02 -0.758 0.448269
## stat66 1.197e-01 7.396e-02 1.618 0.105746
## stat67 -5.111e-02 7.401e-02 -0.691 0.489861
## stat68 -2.164e-02 7.364e-02 -0.294 0.768932
## stat69 -4.749e-02 7.343e-02 -0.647 0.517838
## stat70 2.141e-02 7.308e-02 0.293 0.769559
## stat71 -8.116e-03 7.293e-02 -0.111 0.911394
## stat72 6.709e-02 7.381e-02 0.909 0.363397
## stat73 1.028e-01 7.365e-02 1.396 0.162737
## stat74 -4.545e-02 7.365e-02 -0.617 0.537183
## stat75 -9.223e-02 7.409e-02 -1.245 0.213227
## stat76 5.184e-02 7.402e-02 0.700 0.483692
## stat77 -6.491e-02 7.311e-02 -0.888 0.374659
## stat78 -4.956e-03 7.355e-02 -0.067 0.946284
## stat79 -8.268e-02 7.386e-02 -1.119 0.263011
## stat80 1.379e-02 7.367e-02 0.187 0.851525
## stat81 8.724e-02 7.369e-02 1.184 0.236512
## stat82 -1.815e-02 7.318e-02 -0.248 0.804191
## stat83 -4.484e-02 7.331e-02 -0.612 0.540797
## stat84 -2.824e-02 7.373e-02 -0.383 0.701767
## stat85 -3.663e-02 7.392e-02 -0.495 0.620278
## stat86 1.554e-02 7.344e-02 0.212 0.832475
## stat87 -1.215e-01 7.390e-02 -1.644 0.100184
## stat88 -5.045e-02 7.294e-02 -0.692 0.489172
## stat89 -1.183e-01 7.299e-02 -1.620 0.105281
## stat90 -5.933e-02 7.359e-02 -0.806 0.420126
## stat91 -1.171e-01 7.290e-02 -1.606 0.108296
## stat92 -1.111e-01 7.354e-02 -1.510 0.131075
## stat93 -8.753e-02 7.442e-02 -1.176 0.239594
## stat94 -5.451e-02 7.364e-02 -0.740 0.459156
## stat95 -3.554e-02 7.357e-02 -0.483 0.629081
## stat96 -2.565e-02 7.326e-02 -0.350 0.726278
## stat97 4.633e-02 7.308e-02 0.634 0.526134
## stat98 1.055e+00 7.251e-02 14.552 < 2e-16 ***
## stat99 8.833e-02 7.414e-02 1.191 0.233550
## stat100 1.771e-01 7.358e-02 2.408 0.016084 *
## stat101 -3.040e-02 7.407e-02 -0.410 0.681523
## stat102 4.741e-02 7.414e-02 0.640 0.522513
## stat103 -9.285e-02 7.448e-02 -1.247 0.212553
## stat104 -9.225e-02 7.373e-02 -1.251 0.210885
## stat105 1.178e-01 7.285e-02 1.617 0.105887
## stat106 -5.063e-02 7.329e-02 -0.691 0.489681
## stat107 -6.439e-02 7.340e-02 -0.877 0.380402
## stat108 -7.592e-02 7.324e-02 -1.037 0.299954
## stat109 4.351e-02 7.300e-02 0.596 0.551214
## stat110 -9.473e-01 7.322e-02 -12.937 < 2e-16 ***
## stat111 -7.480e-03 7.334e-02 -0.102 0.918767
## stat112 -5.094e-02 7.345e-02 -0.693 0.488026
## stat113 -5.709e-03 7.385e-02 -0.077 0.938380
## stat114 2.782e-02 7.323e-02 0.380 0.703986
## stat115 7.564e-02 7.310e-02 1.035 0.300867
## stat116 8.560e-02 7.367e-02 1.162 0.245287
## stat117 1.001e-02 7.361e-02 0.136 0.891820
## stat118 -5.185e-02 7.285e-02 -0.712 0.476657
## stat119 1.582e-02 7.381e-02 0.214 0.830343
## stat120 4.674e-02 7.303e-02 0.640 0.522217
## stat121 -2.791e-02 7.336e-02 -0.380 0.703595
## stat122 -4.099e-02 7.315e-02 -0.560 0.575305
## stat123 -3.522e-03 7.426e-02 -0.047 0.962176
## stat124 3.054e-03 7.355e-02 0.042 0.966882
## stat125 -5.011e-03 7.404e-02 -0.068 0.946037
## stat126 1.059e-01 7.298e-02 1.451 0.146801
## stat127 3.245e-02 7.325e-02 0.443 0.657795
## stat128 -8.317e-02 7.320e-02 -1.136 0.255877
## stat129 2.151e-03 7.325e-02 0.029 0.976577
## stat130 8.812e-02 7.382e-02 1.194 0.232675
## stat131 2.410e-02 7.352e-02 0.328 0.743062
## stat132 -5.008e-02 7.285e-02 -0.687 0.491868
## stat133 4.263e-03 7.312e-02 0.058 0.953503
## stat134 -5.617e-02 7.308e-02 -0.769 0.442142
## stat135 -8.440e-02 7.320e-02 -1.153 0.248946
## stat136 6.623e-03 7.353e-02 0.090 0.928235
## stat137 3.377e-02 7.293e-02 0.463 0.643365
## stat138 -2.421e-02 7.343e-02 -0.330 0.741647
## stat139 -8.458e-03 7.385e-02 -0.115 0.908816
## stat140 2.616e-02 7.324e-02 0.357 0.721017
## stat141 4.249e-02 7.292e-02 0.583 0.560108
## stat142 -1.665e-02 7.431e-02 -0.224 0.822749
## stat143 -2.452e-02 7.324e-02 -0.335 0.737845
## stat144 8.083e-02 7.280e-02 1.110 0.266960
## stat145 6.752e-02 7.467e-02 0.904 0.365945
## stat146 -1.305e-01 7.389e-02 -1.766 0.077498 .
## stat147 -7.574e-02 7.405e-02 -1.023 0.306386
## stat148 -7.335e-02 7.268e-02 -1.009 0.312905
## stat149 -1.197e-01 7.417e-02 -1.614 0.106565
## stat150 2.415e-02 7.388e-02 0.327 0.743715
## stat151 -1.248e-01 7.398e-02 -1.686 0.091756 .
## stat152 -5.554e-02 7.321e-02 -0.759 0.448066
## stat153 1.921e-02 7.430e-02 0.259 0.795936
## stat154 -5.250e-02 7.421e-02 -0.707 0.479289
## stat155 -3.410e-02 7.319e-02 -0.466 0.641328
## stat156 1.341e-01 7.391e-02 1.814 0.069713 .
## stat157 1.843e-02 7.306e-02 0.252 0.800881
## stat158 -3.321e-02 7.407e-02 -0.448 0.653914
## stat159 -3.405e-02 7.291e-02 -0.467 0.640469
## stat160 1.743e-02 7.386e-02 0.236 0.813451
## stat161 1.328e-01 7.402e-02 1.794 0.072890 .
## stat162 -2.847e-02 7.293e-02 -0.390 0.696272
## stat163 2.940e-02 7.441e-02 0.395 0.692755
## stat164 4.814e-02 7.381e-02 0.652 0.514332
## stat165 -5.498e-02 7.338e-02 -0.749 0.453671
## stat166 -8.175e-02 7.289e-02 -1.122 0.262121
## stat167 -9.384e-02 7.349e-02 -1.277 0.201657
## stat168 2.385e-02 7.314e-02 0.326 0.744396
## stat169 5.669e-02 7.350e-02 0.771 0.440560
## stat170 -3.048e-02 7.363e-02 -0.414 0.678871
## stat171 5.192e-02 7.401e-02 0.701 0.483020
## stat172 5.933e-02 7.311e-02 0.811 0.417115
## stat173 -4.352e-02 7.362e-02 -0.591 0.554391
## stat174 -6.979e-05 7.314e-02 -0.001 0.999239
## stat175 -9.160e-02 7.384e-02 -1.241 0.214828
## stat176 1.977e-03 7.323e-02 0.027 0.978466
## stat177 -1.259e-02 7.372e-02 -0.171 0.864349
## stat178 -7.905e-02 7.436e-02 -1.063 0.287780
## stat179 3.121e-02 7.346e-02 0.425 0.670936
## stat180 -1.691e-02 7.306e-02 -0.231 0.817022
## stat181 3.100e-02 7.381e-02 0.420 0.674497
## stat182 4.466e-02 7.402e-02 0.603 0.546275
## stat183 6.029e-02 7.343e-02 0.821 0.411587
## stat184 2.268e-02 7.394e-02 0.307 0.759105
## stat185 3.863e-03 7.277e-02 0.053 0.957664
## stat186 -6.503e-02 7.421e-02 -0.876 0.380870
## stat187 -1.030e-01 7.300e-02 -1.411 0.158219
## stat188 2.154e-03 7.319e-02 0.029 0.976519
## stat189 7.173e-02 7.353e-02 0.976 0.329346
## stat190 -4.377e-02 7.317e-02 -0.598 0.549711
## stat191 -5.542e-02 7.359e-02 -0.753 0.451408
## stat192 2.072e-02 7.401e-02 0.280 0.779478
## stat193 -7.708e-02 7.426e-02 -1.038 0.299337
## stat194 -2.953e-02 7.362e-02 -0.401 0.688361
## stat195 8.318e-02 7.352e-02 1.131 0.257894
## stat196 -1.545e-02 7.436e-02 -0.208 0.835392
## stat197 -4.307e-02 7.282e-02 -0.591 0.554285
## stat198 -7.821e-02 7.334e-02 -1.066 0.286341
## stat199 9.467e-02 7.271e-02 1.302 0.192987
## stat200 -1.336e-01 7.278e-02 -1.836 0.066442 .
## stat201 1.650e-02 7.350e-02 0.225 0.822320
## stat202 -4.578e-02 7.392e-02 -0.619 0.535668
## stat203 2.165e-02 7.346e-02 0.295 0.768184
## stat204 -1.313e-01 7.310e-02 -1.796 0.072614 .
## stat205 -8.076e-02 7.276e-02 -1.110 0.267069
## stat206 -2.028e-02 7.407e-02 -0.274 0.784243
## stat207 7.240e-02 7.354e-02 0.984 0.324912
## stat208 -5.495e-03 7.318e-02 -0.075 0.940153
## stat209 -8.333e-03 7.305e-02 -0.114 0.909178
## stat210 -1.116e-02 7.375e-02 -0.151 0.879741
## stat211 2.356e-02 7.313e-02 0.322 0.747348
## stat212 4.807e-02 7.343e-02 0.655 0.512757
## stat213 -7.699e-02 7.366e-02 -1.045 0.296003
## stat214 -1.044e-01 7.319e-02 -1.427 0.153680
## stat215 -7.739e-02 7.356e-02 -1.052 0.292792
## stat216 -7.317e-02 7.350e-02 -0.996 0.319485
## stat217 9.719e-02 7.365e-02 1.320 0.187053
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.659 on 5761 degrees of freedom
## Multiple R-squared: 0.2353, Adjusted R-squared: 0.2034
## F-statistic: 7.385 on 240 and 5761 DF, p-value: < 2.2e-16cd.full = plot.diagnostics(model.full, data.train)
## [1] "Number of data points that have Cook's D > 4/n: 290"
## [1] "Number of data points that have Cook's D > 1: 0"Checking with removal of high influence points
high.cd = names(cd.full[cd.full > 4/nrow(data.train)])
data.train2 = data.train[!(rownames(data.train)) %in% high.cd,]
model.full2 = lm(formula , data.train2)
summary(model.full2)##
## Call:
## lm(formula = formula, data = data.train2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -17.4782 -5.2219 -0.8294 4.7070 21.6283
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.162e+01 2.206e+00 41.530 < 2e-16 ***
## x1 -1.025e-01 1.534e-01 -0.668 0.504240
## x2 7.402e-02 9.819e-02 0.754 0.450961
## x3 1.573e-02 2.684e-02 0.586 0.557986
## x4 -1.549e-02 2.120e-03 -7.307 3.12e-13 ***
## x5 2.218e-01 6.935e-02 3.197 0.001395 **
## x6 -1.629e-01 1.394e-01 -1.169 0.242557
## x7 3.392e+00 1.493e-01 22.717 < 2e-16 ***
## x8 1.777e-01 3.489e-02 5.092 3.66e-07 ***
## x9 8.427e-01 7.780e-02 10.832 < 2e-16 ***
## x10 4.324e-01 7.282e-02 5.938 3.05e-09 ***
## x11 7.434e+07 1.739e+07 4.275 1.94e-05 ***
## x12 9.837e-03 4.404e-02 0.223 0.823254
## x13 3.629e-02 1.762e-02 2.060 0.039479 *
## x14 -7.668e-02 7.593e-02 -1.010 0.312559
## x15 2.598e-02 7.205e-02 0.361 0.718413
## x16 2.585e-01 4.999e-02 5.171 2.42e-07 ***
## x17 3.815e-01 7.621e-02 5.006 5.72e-07 ***
## x18 1.666e+00 5.320e-02 31.322 < 2e-16 ***
## x19 6.986e-02 3.878e-02 1.802 0.071663 .
## x20 3.040e-02 2.698e-01 0.113 0.910308
## x21 4.591e-02 9.926e-03 4.625 3.82e-06 ***
## x22 -2.106e-01 8.140e-02 -2.588 0.009689 **
## x23 3.180e-02 7.679e-02 0.414 0.678825
## stat1 6.529e-03 5.826e-02 0.112 0.910770
## stat2 -2.425e-02 5.829e-02 -0.416 0.677457
## stat3 1.625e-01 5.820e-02 2.791 0.005266 **
## stat4 -9.132e-02 5.852e-02 -1.560 0.118720
## stat5 -2.452e-02 5.828e-02 -0.421 0.674000
## stat6 -4.029e-02 5.860e-02 -0.688 0.491790
## stat7 -3.501e-02 5.809e-02 -0.603 0.546707
## stat8 -3.963e-02 5.832e-02 -0.679 0.496853
## stat9 -5.379e-02 5.825e-02 -0.923 0.355828
## stat10 -7.833e-02 5.833e-02 -1.343 0.179334
## stat11 -8.886e-02 5.867e-02 -1.515 0.129953
## stat12 3.251e-02 5.791e-02 0.561 0.574614
## stat13 -8.737e-02 5.801e-02 -1.506 0.132072
## stat14 -3.152e-01 5.794e-02 -5.440 5.55e-08 ***
## stat15 -1.241e-01 5.792e-02 -2.142 0.032224 *
## stat16 6.364e-03 5.829e-02 0.109 0.913062
## stat17 -3.243e-02 5.793e-02 -0.560 0.575613
## stat18 -3.039e-02 5.781e-02 -0.526 0.599176
## stat19 5.090e-02 5.817e-02 0.875 0.381567
## stat20 -6.549e-03 5.775e-02 -0.113 0.909714
## stat21 -1.683e-02 5.855e-02 -0.287 0.773841
## stat22 -2.276e-02 5.796e-02 -0.393 0.694579
## stat23 1.847e-01 5.799e-02 3.184 0.001458 **
## stat24 -7.747e-02 5.834e-02 -1.328 0.184272
## stat25 -6.796e-02 5.810e-02 -1.170 0.242164
## stat26 -1.311e-01 5.829e-02 -2.249 0.024574 *
## stat27 3.445e-02 5.837e-02 0.590 0.555134
## stat28 7.691e-03 5.852e-02 0.131 0.895441
## stat29 6.623e-02 5.858e-02 1.131 0.258293
## stat30 3.840e-02 5.854e-02 0.656 0.511847
## stat31 4.396e-02 5.881e-02 0.747 0.454846
## stat32 -1.810e-02 5.876e-02 -0.308 0.758021
## stat33 -1.225e-01 5.803e-02 -2.111 0.034805 *
## stat34 1.011e-01 5.828e-02 1.734 0.082886 .
## stat35 -1.671e-01 5.835e-02 -2.864 0.004200 **
## stat36 1.363e-02 5.788e-02 0.235 0.813890
## stat37 -5.675e-02 5.870e-02 -0.967 0.333714
## stat38 1.166e-01 5.839e-02 1.997 0.045889 *
## stat39 4.470e-03 5.776e-02 0.077 0.938322
## stat40 -5.271e-02 5.810e-02 -0.907 0.364322
## stat41 -2.181e-01 5.799e-02 -3.761 0.000171 ***
## stat42 -5.497e-02 5.828e-02 -0.943 0.345624
## stat43 -6.626e-02 5.825e-02 -1.137 0.255383
## stat44 3.415e-02 5.836e-02 0.585 0.558427
## stat45 -9.391e-02 5.817e-02 -1.614 0.106492
## stat46 3.137e-02 5.854e-02 0.536 0.592024
## stat47 4.425e-02 5.878e-02 0.753 0.451649
## stat48 1.541e-02 5.815e-02 0.265 0.791078
## stat49 2.988e-02 5.802e-02 0.515 0.606627
## stat50 5.704e-02 5.778e-02 0.987 0.323605
## stat51 5.488e-02 5.832e-02 0.941 0.346709
## stat52 1.594e-02 5.835e-02 0.273 0.784707
## stat53 -1.800e-02 5.837e-02 -0.308 0.757847
## stat54 -1.353e-01 5.902e-02 -2.292 0.021949 *
## stat55 5.806e-02 5.801e-02 1.001 0.316992
## stat56 -3.793e-03 5.840e-02 -0.065 0.948221
## stat57 -9.178e-03 5.796e-02 -0.158 0.874180
## stat58 -2.139e-02 5.740e-02 -0.373 0.709404
## stat59 1.216e-01 5.812e-02 2.093 0.036376 *
## stat60 1.604e-01 5.866e-02 2.734 0.006269 **
## stat61 -1.126e-01 5.835e-02 -1.929 0.053752 .
## stat62 -7.039e-02 5.813e-02 -1.211 0.225997
## stat63 9.366e-02 5.844e-02 1.603 0.109031
## stat64 -2.746e-02 5.804e-02 -0.473 0.636170
## stat65 -2.773e-02 5.847e-02 -0.474 0.635270
## stat66 7.156e-02 5.865e-02 1.220 0.222468
## stat67 5.805e-02 5.862e-02 0.990 0.322109
## stat68 -4.149e-02 5.831e-02 -0.711 0.476829
## stat69 -6.837e-02 5.813e-02 -1.176 0.239608
## stat70 6.633e-02 5.793e-02 1.145 0.252244
## stat71 -1.868e-03 5.790e-02 -0.032 0.974269
## stat72 6.323e-02 5.858e-02 1.079 0.280443
## stat73 1.032e-01 5.847e-02 1.764 0.077717 .
## stat74 -8.801e-03 5.830e-02 -0.151 0.880013
## stat75 -3.407e-02 5.861e-02 -0.581 0.561020
## stat76 3.009e-02 5.855e-02 0.514 0.607385
## stat77 1.446e-02 5.791e-02 0.250 0.802792
## stat78 -3.704e-02 5.804e-02 -0.638 0.523401
## stat79 2.147e-02 5.838e-02 0.368 0.713145
## stat80 1.695e-02 5.836e-02 0.290 0.771454
## stat81 6.051e-02 5.842e-02 1.036 0.300347
## stat82 -5.341e-02 5.794e-02 -0.922 0.356666
## stat83 -3.738e-02 5.801e-02 -0.644 0.519332
## stat84 -1.812e-02 5.847e-02 -0.310 0.756610
## stat85 -1.130e-01 5.863e-02 -1.927 0.054046 .
## stat86 5.573e-02 5.819e-02 0.958 0.338221
## stat87 -1.039e-01 5.850e-02 -1.775 0.075928 .
## stat88 2.253e-03 5.789e-02 0.039 0.968954
## stat89 -5.473e-02 5.799e-02 -0.944 0.345342
## stat90 -7.972e-02 5.834e-02 -1.367 0.171809
## stat91 -1.115e-01 5.766e-02 -1.933 0.053226 .
## stat92 -6.816e-02 5.824e-02 -1.170 0.241877
## stat93 -3.492e-02 5.919e-02 -0.590 0.555266
## stat94 2.246e-02 5.823e-02 0.386 0.699668
## stat95 4.687e-02 5.835e-02 0.803 0.421858
## stat96 -1.104e-02 5.813e-02 -0.190 0.849332
## stat97 6.338e-02 5.787e-02 1.095 0.273439
## stat98 9.648e-01 5.751e-02 16.777 < 2e-16 ***
## stat99 9.347e-02 5.883e-02 1.589 0.112180
## stat100 1.500e-01 5.832e-02 2.572 0.010148 *
## stat101 2.898e-02 5.875e-02 0.493 0.621792
## stat102 5.430e-02 5.875e-02 0.924 0.355315
## stat103 -9.929e-02 5.882e-02 -1.688 0.091493 .
## stat104 -4.042e-02 5.856e-02 -0.690 0.490074
## stat105 1.175e-01 5.768e-02 2.037 0.041714 *
## stat106 -1.202e-01 5.799e-02 -2.074 0.038158 *
## stat107 -3.054e-02 5.812e-02 -0.526 0.599252
## stat108 -5.591e-02 5.809e-02 -0.962 0.335905
## stat109 7.552e-04 5.788e-02 0.013 0.989591
## stat110 -8.629e-01 5.789e-02 -14.905 < 2e-16 ***
## stat111 6.237e-03 5.799e-02 0.108 0.914352
## stat112 -5.017e-02 5.823e-02 -0.862 0.388929
## stat113 -9.494e-03 5.840e-02 -0.163 0.870860
## stat114 6.319e-02 5.808e-02 1.088 0.276639
## stat115 9.826e-02 5.798e-02 1.695 0.090166 .
## stat116 6.625e-02 5.835e-02 1.135 0.256245
## stat117 4.569e-03 5.815e-02 0.079 0.937381
## stat118 -1.069e-02 5.763e-02 -0.185 0.852861
## stat119 5.674e-02 5.846e-02 0.970 0.331861
## stat120 -2.671e-02 5.776e-02 -0.462 0.643807
## stat121 -1.087e-02 5.810e-02 -0.187 0.851536
## stat122 -5.585e-02 5.808e-02 -0.962 0.336318
## stat123 1.068e-01 5.882e-02 1.815 0.069582 .
## stat124 -1.605e-02 5.826e-02 -0.275 0.783006
## stat125 -1.385e-02 5.866e-02 -0.236 0.813388
## stat126 6.977e-02 5.781e-02 1.207 0.227558
## stat127 -3.234e-02 5.801e-02 -0.557 0.577293
## stat128 -2.014e-01 5.792e-02 -3.477 0.000511 ***
## stat129 -1.094e-02 5.791e-02 -0.189 0.850233
## stat130 7.619e-02 5.851e-02 1.302 0.192898
## stat131 4.175e-03 5.825e-02 0.072 0.942869
## stat132 -5.578e-02 5.768e-02 -0.967 0.333513
## stat133 9.534e-03 5.801e-02 0.164 0.869463
## stat134 -3.643e-02 5.782e-02 -0.630 0.528665
## stat135 -7.629e-02 5.804e-02 -1.314 0.188742
## stat136 -8.386e-03 5.823e-02 -0.144 0.885496
## stat137 7.208e-02 5.778e-02 1.247 0.212280
## stat138 -3.302e-02 5.812e-02 -0.568 0.569963
## stat139 -1.631e-02 5.858e-02 -0.278 0.780756
## stat140 1.552e-02 5.790e-02 0.268 0.788696
## stat141 6.877e-02 5.780e-02 1.190 0.234161
## stat142 8.816e-03 5.894e-02 0.150 0.881120
## stat143 -5.405e-02 5.800e-02 -0.932 0.351422
## stat144 8.790e-02 5.760e-02 1.526 0.127064
## stat145 4.046e-02 5.927e-02 0.683 0.494868
## stat146 -1.328e-01 5.861e-02 -2.265 0.023530 *
## stat147 -7.392e-02 5.875e-02 -1.258 0.208366
## stat148 -4.502e-02 5.775e-02 -0.780 0.435651
## stat149 -1.166e-01 5.893e-02 -1.979 0.047830 *
## stat150 -5.721e-03 5.871e-02 -0.097 0.922376
## stat151 -2.396e-02 5.874e-02 -0.408 0.683390
## stat152 -3.838e-02 5.794e-02 -0.662 0.507735
## stat153 3.359e-02 5.880e-02 0.571 0.567890
## stat154 3.264e-02 5.882e-02 0.555 0.579012
## stat155 1.470e-02 5.808e-02 0.253 0.800169
## stat156 1.076e-01 5.850e-02 1.839 0.065971 .
## stat157 2.949e-04 5.780e-02 0.005 0.995930
## stat158 4.493e-02 5.868e-02 0.766 0.443887
## stat159 -1.003e-02 5.789e-02 -0.173 0.862388
## stat160 3.010e-02 5.865e-02 0.513 0.607853
## stat161 9.716e-02 5.861e-02 1.658 0.097462 .
## stat162 -3.401e-02 5.773e-02 -0.589 0.555777
## stat163 3.840e-02 5.916e-02 0.649 0.516264
## stat164 1.273e-02 5.859e-02 0.217 0.827969
## stat165 -2.131e-02 5.823e-02 -0.366 0.714423
## stat166 -6.589e-02 5.764e-02 -1.143 0.253009
## stat167 -1.473e-01 5.822e-02 -2.531 0.011405 *
## stat168 5.791e-03 5.788e-02 0.100 0.920312
## stat169 3.705e-02 5.843e-02 0.634 0.526046
## stat170 1.251e-02 5.839e-02 0.214 0.830298
## stat171 -3.397e-02 5.869e-02 -0.579 0.562735
## stat172 1.083e-01 5.780e-02 1.873 0.061083 .
## stat173 1.446e-02 5.826e-02 0.248 0.803961
## stat174 5.670e-02 5.797e-02 0.978 0.328148
## stat175 -9.406e-02 5.852e-02 -1.607 0.108077
## stat176 -6.574e-02 5.799e-02 -1.134 0.256987
## stat177 -9.208e-02 5.843e-02 -1.576 0.115103
## stat178 -3.661e-02 5.889e-02 -0.622 0.534136
## stat179 -9.267e-03 5.815e-02 -0.159 0.873399
## stat180 5.192e-03 5.801e-02 0.090 0.928683
## stat181 5.751e-02 5.846e-02 0.984 0.325257
## stat182 8.915e-02 5.872e-02 1.518 0.129039
## stat183 5.543e-02 5.838e-02 0.949 0.342492
## stat184 1.112e-01 5.862e-02 1.897 0.057853 .
## stat185 3.505e-02 5.770e-02 0.607 0.543571
## stat186 4.305e-02 5.882e-02 0.732 0.464285
## stat187 -2.516e-02 5.783e-02 -0.435 0.663469
## stat188 2.084e-02 5.807e-02 0.359 0.719761
## stat189 3.457e-03 5.828e-02 0.059 0.952699
## stat190 -6.668e-02 5.794e-02 -1.151 0.249904
## stat191 -3.506e-02 5.827e-02 -0.602 0.547420
## stat192 1.508e-02 5.867e-02 0.257 0.797137
## stat193 -9.102e-03 5.887e-02 -0.155 0.877134
## stat194 -7.363e-02 5.843e-02 -1.260 0.207699
## stat195 -9.135e-03 5.832e-02 -0.157 0.875533
## stat196 -2.188e-02 5.902e-02 -0.371 0.710848
## stat197 -6.382e-02 5.782e-02 -1.104 0.269707
## stat198 -7.797e-02 5.806e-02 -1.343 0.179332
## stat199 6.378e-02 5.765e-02 1.106 0.268598
## stat200 -9.227e-02 5.782e-02 -1.596 0.110608
## stat201 8.397e-02 5.839e-02 1.438 0.150477
## stat202 -1.672e-03 5.869e-02 -0.028 0.977279
## stat203 5.197e-02 5.809e-02 0.895 0.370967
## stat204 -6.238e-02 5.799e-02 -1.076 0.282107
## stat205 1.016e-02 5.743e-02 0.177 0.859590
## stat206 -7.782e-02 5.872e-02 -1.325 0.185153
## stat207 1.137e-01 5.838e-02 1.948 0.051438 .
## stat208 2.788e-02 5.801e-02 0.481 0.630740
## stat209 -1.444e-02 5.779e-02 -0.250 0.802756
## stat210 -6.708e-02 5.844e-02 -1.148 0.251075
## stat211 4.201e-02 5.802e-02 0.724 0.469058
## stat212 8.656e-02 5.821e-02 1.487 0.137063
## stat213 -2.598e-02 5.825e-02 -0.446 0.655636
## stat214 -9.299e-02 5.803e-02 -1.602 0.109145
## stat215 -5.089e-02 5.837e-02 -0.872 0.383374
## stat216 -1.117e-01 5.812e-02 -1.921 0.054743 .
## stat217 7.245e-02 5.838e-02 1.241 0.214692
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.458 on 5471 degrees of freedom
## Multiple R-squared: 0.3347, Adjusted R-squared: 0.3055
## F-statistic: 11.47 on 240 and 5471 DF, p-value: < 2.2e-16cd.full2 = plot.diagnostics(model.full2, data.train2)
## [1] "Number of data points that have Cook's D > 4/n: 307"
## [1] "Number of data points that have Cook's D > 1: 0"# much more normal residuals than before.
# See if you can check the distribution (boxplots) of the high leverage points and the other pointsmodel.null = lm(grand.mean.formula, data.train)
# summary(model.null)
# plot.diagnostics(model.null, data.train)model.null2 = lm(grand.mean.formula, data.train2)
# summary(model.null2)
# plot.diagnostics(model.null2, data.train2)Variable Selection
Basic: http://www.stat.columbia.edu/~martin/W2024/R10.pdf Cross Validation + Other Metrics: http://www.sthda.com/english/articles/37-model-selection-essentials-in-r/154-stepwise-regression-essentials-in-r/
Forward Selection (w/ full train)
Train
if (algo.forward == TRUE){
t1 = Sys.time()
model.forward = step(model.null, scope=list(lower=model.null, upper=model.full), direction="forward", trace = 0)
print(summary(model.forward))
#saveRDS(model.forward,file = "model_forward.rds")
t2 = Sys.time()
print (paste("Time taken for Forward Selection: ",t2-t1, sep = ""))
plot.diagnostics(model.forward, data.train)
}Test
if (algo.forward == TRUE){
test.model(model.forward, data.test, "Forward Selection")
}Forward Selection (w/ filtered train)
Train
if (algo.forward == TRUE){
t1 = Sys.time()
model.forward2 = step(model.null2, scope=list(lower=model.null2, upper=model.full2), direction="forward", trace = 0)
print(summary(model.forward2))
#saveRDS(model.forward,file = "model_forward.rds")
t2 = Sys.time()
print (paste("Time taken for Forward Selection: ",t2-t1, sep = ""))
plot.diagnostics(model.forward2, data.train2)
}Test
if (algo.forward == TRUE){
test.model(model.forward2, data.test, "Forward Selection (2)")
}Forward Selection with CV (w/ full train)
Train
if (algo.forward.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
, data = data.train
, method = "leapForward"
, feature.names = feature.names)
model.forward = returned$model
id = returned$id
}Test
if (algo.forward.caret == TRUE){
test.model(model.forward, data.test
,method = 'leapForward',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,id = id
,draw.limits = TRUE)
}Forward Selection with CV (w/ filtered train)
Train
if (algo.forward.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train2
,method = "leapForward"
,feature.names = feature.names)
model.forward = returned$model
id = returned$id
}Test
if (algo.forward.caret == TRUE){
test.model(model.forward, data.test
,method = 'leapForward',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,id = id
,draw.limits = TRUE)
}Backward Elimination
Train
if (algo.backward == TRUE){
# Takes too much time
t1 = Sys.time()
model.backward = step(model.full, data = data.train, direction="backward", trace = 0)
print(summary(model.backward))
#saveRDS(model.forward,file = "model_backward.rds")
t2 = Sys.time()
print (paste("Time taken for Backward Elimination: ",t2-t1, sep = ""))
plot.diagnostics(model.backward, data.train)
}Test
if (algo.backward == TRUE){
test.model(model.backard, data.test, "Backward Elimination")
}Backward Elimination with CV (w/ full train)
Train
if (algo.backward.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train
,method = "leapBackward"
,feature.names = feature.names)
model.backward = returned$model
id = returned$id
}Test
if (algo.backward.caret == TRUE){
test.model(model.backward, data.test
,method = 'leapBackward',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,id = id
,draw.limits = TRUE)
}Backward Elimination with CV (w/ filtered train)
Train
if (algo.backward.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train2
,method = "leapBackward"
,feature.names = feature.names)
model.backward = returned$model
id = returned$id
}Test
if (algo.backward.caret == TRUE){
test.model(model.backward, data.test
,method = 'leapBackward',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,id = id
,draw.limits = TRUE)
}Stepwise Selection (w/ full train)
Train
if (algo.stepwise == TRUE){
t1 = Sys.time()
model.stepwise = step(model.null, scope=list(upper=model.full), data = data.train, direction="both", trace = 0)
print(summary(model.stepwise))
#saveRDS(model.stepwise,file = "model_stepwise.rds")
t2 = Sys.time()
print (paste("Time taken for Stepwise Selection: ",t2-t1, sep = ""))
plot.diagnostics(model.stepwise, data.train)
}Test
if (algo.stepwise == TRUE){
test.model(model.stepwise, data.test, "Stepwise Selection")
}Stepwise Selection (w/ filtered train)
Train
if (algo.stepwise == TRUE){
t1 = Sys.time()
model.stepwise2 = step(model.null2, scope=list(upper=model.full2), data = data.train2, direction="both", trace = 0)
print(summary(model.stepwise2))
#saveRDS(model.forward,file = "model_stepwise.rds")
t2 = Sys.time()
print (paste("Time taken for Stepwise Selection: ",t2-t1, sep = ""))
plot.diagnostics(model.stepwise2, data.train2)
}Test
if (algo.stepwise == TRUE){
test.model(model.stepwise2, data.test, "Stepwise Selection (2)")
}Stepwise Selection with CV (w/ full train)
Train
if (algo.stepwise.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train
,method = "leapSeq"
,feature.names = feature.names)
model.stepwise = returned$model
id = returned$id
}Test
if (algo.stepwise.caret == TRUE){
# test.model(model.stepwise, data.test, "Stepwise Selection", draw.limits = TRUE, regsubset = TRUE, id = id, formula = formula)
test.model(model.stepwise, data.test
,method = 'leapSeq',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,id = id
,draw.limits = TRUE)
}Stepwise Selection with CV (w/ filtered train)
Train
Test
LASSO (w/ full train)
Train
if(algo.LASSO == TRUE){
# Formatting data for GLM net
# you can use model.matrix as well -- model.matrix creates a design (or model) matrix,
# e.g., by expanding factors to a set of dummy variables (depending on the contrasts)
# and expanding interactions similarly.
x = as.matrix(data.train[,feature.names])
y = data.train[,label.names]
xtest = as.matrix(data.test[,feature.names])
ytest = data.test[,label.names]
grid=10^seq(10,-2, length =100)
set.seed(1)
model.LASSO=glmnet(x,y,alpha=1, lambda =grid)
cv.out=cv.glmnet(x,y,alpha=1) # alpha=1 performs LASSO
plot(cv.out)
bestlambda<-cv.out$lambda.min # Optimal penalty parameter. You can make this call visually.
print(coef(model.LASSO,s=bestlambda))
}Test
if(algo.LASSO == TRUE){
lasso.pred=predict (model.LASSO ,s=bestlambda ,newx=xtest)
testMSE_LASSO = mean((ytest-lasso.pred)^2)
print (paste("LASSO Test RMSE: ",testMSE_LASSO, sep=""))
plot(ytest,lasso.pred)
}LASSO (w/ filtered train)
Train
if(algo.LASSO == TRUE){
# Formatting data for GLM net
# you can use model.matrix as well -- model.matrix creates a design (or model) matrix,
# e.g., by expanding factors to a set of dummy variables (depending on the contrasts)
# and expanding interactions similarly.
x = as.matrix(data.train2[,feature.names])
y = data.train2[,label.names]
xtest = as.matrix(data.test[,feature.names])
ytest = data.test[,label.names]
grid=10^seq(10,-2, length =100)
set.seed(1)
model.LASSO=glmnet(x,y,alpha=1, lambda =grid)
cv.out=cv.glmnet(x,y,alpha=1) # alpha=1 performs LASSO
plot(cv.out)
bestlambda<-cv.out$lambda.min # Optimal penalty parameter. You can make this call visually.
print(coef(model.LASSO,s=bestlambda))
}Test
if(algo.LASSO == TRUE){
lasso.pred=predict (model.LASSO ,s=bestlambda ,newx=xtest)
testMSE_LASSO = mean((ytest-lasso.pred)^2)
print (paste("LASSO Test RMSE: ",testMSE_LASSO, sep=""))
plot(ytest,lasso.pred)
}LASSO with CV (w/ full train)
Train
if (algo.LASSO.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train
,method = "glmnet"
,subopt = 'LASSO'
,feature.names = feature.names)
model.LASSO.caret = returned$model
}Test
if (algo.LASSO.caret == TRUE){
test.model(model.LASSO.caret, data.test
,method = 'glmnet',subopt = "LASSO"
,formula = formula, feature.names = feature.names, label.names = label.names
,draw.limits = TRUE)
}LASSO with CV (w/ filtered train)
Train
if (algo.LASSO.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train2
,method = "glmnet"
,subopt = 'LASSO'
,feature.names = feature.names)
model.LASSO.caret = returned$model
}Test
if (algo.LASSO.caret == TRUE){
test.model(model.LASSO.caret, data.test
,method = 'glmnet',subopt = "LASSO"
,formula = formula, feature.names = feature.names, label.names = label.names
,draw.limits = TRUE)
}LARS with CV (w/ full train)
Train
if (algo.LARS.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train
,method = "lars"
,subopt = 'NULL'
,feature.names = feature.names)
model.LARS.caret = returned$model
}Test
if (algo.LARS.caret == TRUE){
test.model(model.LARS.caret, data.test
,method = 'lars',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,draw.limits = TRUE)
}LARS with CV (w/ filtered train)
Train
if (algo.LARS.caret == TRUE){
set.seed(1)
returned = train.caret.glmselect(formula = formula
,data = data.train2
,method = "lars"
,subopt = 'NULL'
,feature.names = feature.names)
model.LARS.caret = returned$model
}Test
if (algo.LARS.caret == TRUE){
test.model(model.LARS.caret, data.test
,method = 'lars',subopt = NULL
,formula = formula, feature.names = feature.names, label.names = label.names
,draw.limits = TRUE)
}